CN114882902A

Movatterモバイル変換

Info

Publication number: CN114882902A
Application number: CN202210468564.2A
Authority: CN
Inventors: 江益靓
Original assignee: Tencent Music Entertainment Technology Shenzhen Co Ltd
Current assignee: Tencent Music Entertainment Technology Shenzhen Co Ltd
Priority date: 2022-04-29
Filing date: 2022-04-29
Publication date: 2022-08-09
Anticipated expiration: 2042-04-29

Abstract

The embodiment of the invention provides an audio-based game beat point mapping method and a related device, which are used for correcting Onstet (sound energy catastrophe point) in audio to be detected by combining beat information of music and mapping the corrected sound energy catastrophe point to an interaction point in a music game, so that the regularity of the interaction point in the music game is improved. The method comprises the following steps: acquiring audio to be detected; identifying an initial sound energy catastrophe point in the audio to be detected; acquiring beat information of the audio to be detected; correcting the initial sound energy catastrophe point in the audio to be detected by combining the beat information of the audio to be detected to obtain a corrected sound energy catastrophe point; and mapping the modified sound energy catastrophe points to interaction points in the music game.

Description

Translated fromChinese

技术领域technical field

本发明涉及音乐数据处理技术领域，尤其涉及一种基于音频的游戏拍点映射方法及相关装置。The present invention relates to the technical field of music data processing, in particular to an audio-based game beat mapping method and related devices.

背景技术Background technique

音乐游戏拍点：是指用户用根据歌曲律动信息，根据给定的敲击点，完成对应的敲击。根据用户命中敲击点的位置进行计分，完成度越高，分数越高。常见的音乐游戏拍点设计是人工根据歌曲律动信息进行设置。Music game beat point: It means that the user uses the rhythm information according to the song to complete the corresponding tap according to the given tap point. Scoring is performed according to the position where the user hits the tap point, and the higher the degree of completion, the higher the score. Common music game beat design is manually set according to song rhythm information.

传统的游戏拍点只是基于音频中的Onset(声音能量突变点)点来设置对对应的敲击点，但传统的Onset的识别方法，容易受乐曲中的乐器、人声等因素的影响，从而使得音频中检测到的Onset较为杂乱。The traditional game beat point is only based on the Onset (sound energy mutation point) point in the audio to set the corresponding tap point, but the traditional Onset recognition method is easily affected by the musical instruments, vocals and other factors in the music, so Makes the Onset detected in the audio more cluttered.

发明内容SUMMARY OF THE INVENTION

本发明实施例提供了一种基于音频的游戏拍点映射方法及相关装置，用于结合乐曲的节拍信息对待检测音频中的Onset(声音能量突变点)进行修正，并将修正后的声音能量突变点映射为音乐游戏中的互动点，从而提升音乐游戏中互动点的律动性。Embodiments of the present invention provide an audio-based game beat mapping method and a related device, which are used to correct the Onset (sound energy mutation point) in the audio to be detected in combination with the beat information of the music piece, and change the corrected sound energy mutation point The points are mapped to the interactive points in the music game, thereby improving the rhythm of the interactive points in the music game.

本申请实施例第一方面提供了一种基于音频的游戏拍点映射方法，所述方法包括：A first aspect of the embodiments of the present application provides an audio-based game beat mapping method, the method comprising:

获取待检测音频；Get the audio to be detected;

识别出所述待检测音频中的初始声音能量突变点；Identifying the initial sound energy mutation point in the audio to be detected;

获取所述待检测音频的节拍信息；Obtain the beat information of the audio to be detected;

结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；Combining the beat information of the audio to be detected, correcting the initial sound energy mutation point in the audio to be detected to obtain the corrected sound energy mutation point;

将所述修正后的声音能量突变点映射为音乐游戏中的互动点。The modified sound energy mutation point is mapped to the interaction point in the music game.

可选的，述获取所述待检测音频的节拍信息，包括：Optionally, obtaining the beat information of the audio to be detected includes:

基于信号处理或深度学习神经网络模型检测出所述待检测音频中的拍点信息和重拍信息；Detecting beat information and rebeat information in the audio to be detected based on signal processing or a deep learning neural network model;

获取所述重拍信息和所述拍点信息在所述待检测音频中的分布规律；Obtain the distribution rule of the rebeat information and the beat information in the audio to be detected;

根据所述分布规律，获取所述待检测音频的拍型信息。According to the distribution rule, the beat pattern information of the audio to be detected is acquired.

可选的，所述节拍信息包括所述拍型信息和单位时间内的节拍数；Optionally, the beat information includes the beat pattern information and the beat number per unit time;

所述结合所述待检测音频的节拍信息，对所述待检测音频中的声音能量突变点进行修正，以得到修正后的声音能量突变点，包括：The sound energy mutation point in the to-be-detected audio is modified in combination with the beat information of the audio to be detected, so as to obtain the corrected sound energy mutation point, including:

根据所述待检测音频的拍型信息和单位时间内的节拍数，计算所述初始声音能量突变点出现的最小时间间隔；According to the beat pattern information of the to-be-detected audio and the beat number per unit time, calculate the minimum time interval for the occurrence of the initial sound energy mutation point;

若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作和/或调整操作，以得到修正后的声音能量突变点。If multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, perform a deletion operation and/or an adjustment operation on the multiple initial sound energy mutation points to obtain a modified sound Energy mutation point.

可选的，所述若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作，包括：Optionally, if multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, performing a deletion operation on the multiple initial sound energy mutation points, including:

若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则将所述多个初始声音能量突变点中的至少两个初始声量突变点合并为一个初始声音能量突变点。If multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, at least two initial sound energy mutation points among the multiple initial sound energy mutation points are combined into one initial sound energy mutation point.

可选的，在将所述多个初始声音能量突变点中的至少两个初始声音能量突变点合并为一个初始声音能量突变点之后，所述方法还包括：Optionally, after combining at least two initial sound energy mutation points of the plurality of initial sound energy mutation points into one initial sound energy mutation point, the method further includes:

根据所述待检测音频的拍型信息，获取待检测音频相邻拍点内允许出现声音能量突变点的最大数量；According to the beat pattern information of the audio to be detected, obtain the maximum number of sound energy mutation points allowed to appear in the adjacent beat points of the audio to be detected;

若在所述待检测音频相邻拍点内出现初始声音能量突变点的数量大于所述最大数量，则删除所述最大数量以外的其他初始声音能量突变点。If the number of initial sound energy mutation points in the adjacent beat points of the audio to be detected is greater than the maximum number, other initial sound energy mutation points other than the maximum number are deleted.

可选的，所述若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行调整操作，包括：Optionally, if multiple initial sound energy mutation points occur within a time period not greater than half of the minimum time interval, performing an adjustment operation on the multiple initial sound energy mutation points, including:

获取所述最大数量的初始声音能量突变点所在相邻拍点间的时间段；Obtain the time period between the adjacent beat points where the maximum number of initial sound energy mutation points are located;

将所述最大数量的初始声音能量突变点均分至所述时间段内的各个时刻。The maximum number of initial sound energy abrupt changes are equally divided into each moment in the time period.

可选的，所述方法还包括：Optionally, the method further includes:

识别出所述待检测音频中的拍点信息、重拍信息和长拍信息中的至少一项；Identifying at least one item of beat information, rebeat information and long beat information in the audio to be detected;

将所述待检测音频中的拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点。At least one item of beat information, rebeat information and long beat information in the audio to be detected is mapped to an interaction point in the music game.

可选的，所述识别出所述待检测音频中的长拍信息，包括：Optionally, the identifying the long-beat information in the audio to be detected includes:

获取所述待检测音频中每个音符和/或每个歌词的起始时刻和/或持续时长；Obtain the start time and/or duration of each note and/or each lyrics in the audio to be detected;

将持续时长大于第一预设时长的音符和/或歌词，确定为所述待检测音频中的长拍信息。The notes and/or lyrics whose duration is longer than the first preset duration are determined as long beat information in the audio to be detected.

可选的，所述识别出所述待检测音频中的拍点信息和/或重拍信息，包括：Optionally, identifying the beat information and/or retake information in the audio to be detected includes:

基于信号处理或深度学习神经网络模型检测出所述待检测音频中拍点信息和/或重拍信息。The beat information and/or the rebeat information in the audio to be detected is detected based on signal processing or a deep learning neural network model.

可选的，在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，所述方法还包括：Optionally, before mapping the corrected sound energy mutation point in the to-be-detected audio and at least one of the beat information, the rebeat information and the long beat information as the interactive point in the music game, the The method also includes:

依次标记出所述待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点；Marking the long beat information, rebeat information, beat point information and the corrected sound energy mutation point in the audio to be detected in turn;

若所述修正后的声音能量突变点与所述重拍信息和/或所述拍点信息重叠，则将所述修正后的声音能量突变点标记为所述重拍信息和/或所述拍点信息。If the modified sound energy mutation point overlaps with the rebeat information and/or the beat point information, marking the corrected sound energy mutation point as the rebeat information and/or the beat information point information.

可选的，所述将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点，包括：Optionally, the modified sound energy mutation point in the to-be-detected audio and at least one of the beat information, the rebeat information and the long beat information are mapped to the interactive points in the music game, including: :

将所述修改后的声音能量突变点映射为音乐游戏中的单击，和/或；mapping the modified sound energy breakpoints to clicks in the music game, and/or;

将所述拍点信息映射为音乐游戏中的单击；和/或；mapping the beat information to a click in a music game; and/or;

将所述重拍信息映射为音乐游戏中的双击；和/或；mapping the remake information to a double tap in a music game; and/or;

将所述长拍信息映射为音乐游戏中预设时长的连续按压。The long-beat information is mapped to continuous pressing of a preset duration in the music game.

可选的，在识别出所述待检测音频中的初始声音能量突变点之前，所述方法还包括：Optionally, before identifying the initial sound energy mutation point in the audio to be detected, the method further includes:

对所述待检测音频执行预处理，以减少所述待检测音频的数据处理量，其中，所述预处理包括将所述待检测音频转换为单声道语音信号和将所述待检测音频的采样率重采样至标准采样率中的至少一项。Preprocessing is performed on the audio to be detected to reduce the data processing amount of the audio to be detected, wherein the preprocessing includes converting the audio to be detected into a monophonic voice signal and converting the audio to be detected. The sample rate is resampled to at least one of the standard sample rates.

本申请实施例第二方面提供了一种基于音频的游戏拍点映射装置，所述装置包括：A second aspect of the embodiments of the present application provides an audio-based game beat mapping device, the device comprising:

获取单元，用于获取待检测音频；an acquisition unit for acquiring the audio to be detected;

识别单元，用于识别出所述待检测音频中的初始声音能量突变点；an identification unit for identifying the initial sound energy mutation point in the audio to be detected;

所述获取单元，还用于获取所述待检测音频的节拍信息；The acquiring unit is further configured to acquire beat information of the audio to be detected;

修正单元，用于结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；a correction unit, configured to correct the initial sound energy mutation point in the to-be-detected audio in combination with the beat information of the to-be-detected audio, so as to obtain the corrected sound energy mutation point;

映射单元，用于将所述修正后的声音能量突变点映射为音乐游戏中的互动点。The mapping unit is used for mapping the modified sound energy mutation point to the interaction point in the music game.

可选的，所述获取单元具体用于：Optionally, the obtaining unit is specifically used for:

所述修正单元具体用于：The correction unit is specifically used for:

可选的，所述修正单元具体用于：Optionally, the correction unit is specifically used for:

可选的，所述修正单元具还用于：Optionally, the correction unit is also used for:

可选的，所述装置还包括：Optionally, the device further includes:

识别单元，用于识别出所述待检测音频中的拍点信息、重拍信息和长拍信息中的至少一项；an identification unit, configured to identify at least one of beat information, rebeat information and long beat information in the audio to be detected;

所述映射单元，还用于：The mapping unit is also used for:

可选的，所述识别单元具体用于：Optionally, the identifying unit is specifically used for:

可选的，所述装置还包括：Optionally, the device further includes:

标记单元，用于在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，依次标记出所述待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点；a marking unit, configured to map the modified sound energy mutation point in the audio to be detected and at least one of the beat information, the rebeat information and the long beat information as the interactive point in the music game, Marking the long beat information, rebeat information, beat point information and the corrected sound energy mutation point in the audio to be detected in turn;

所述标记单元，还用于若所述修正后的声音能量突变点与所述重拍信息和/或所述拍点信息重叠，则将所述修正后的声音能量突变点标记为所述重拍信息和/或所述拍点信息。The marking unit is further configured to mark the corrected sound energy mutation point as the rebeat information if the modified sound energy mutation point overlaps with the rebeat information and/or the beat point information. beat information and/or the beat point information.

可选的，所述映射单元具体用于：Optionally, the mapping unit is specifically used for:

可选的，所述装置还包括：Optionally, the device further includes:

预处理单元，用于在识别出所述待检测音频中的初始声音能量突变点之前，对所述待检测音频执行预处理，以减少所述待检测音频的数据处理量，其中，所述预处理包括将所述待检测音频转换为单声道语音信号和将所述待检测音频的采样率重采样至标准采样率中的至少一项。A preprocessing unit, configured to perform preprocessing on the audio to be detected before identifying the initial sound energy mutation point in the audio to be detected, so as to reduce the data processing amount of the audio to be detected, wherein the preprocessing Processing includes at least one of converting the audio to be detected to a monophonic speech signal and resampling the sampling rate of the audio to be detected to a standard sampling rate.

本申请实施例还提供了一种计算机装置，包括处理器和存储器，处理器在执行存储于存储器上的计算机程序时，用于实现本申请实施例第一方面所述的基于音频的游戏拍点映射方法。Embodiments of the present application further provide a computer device, including a processor and a memory, when the processor executes a computer program stored in the memory, the processor is configured to implement the audio-based game beats described in the first aspect of the embodiments of the present application mapping method.

本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时，用于实现本申请实施例第一方面所述的基于音频的游戏拍点映射法。Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, is used to implement the audio-based game beats described in the first aspect of the embodiments of the present application mapping method.

从以上技术方案可以看出，本发明实施例具有以下优点：As can be seen from the above technical solutions, the embodiments of the present invention have the following advantages:

本申请实施例中，获取待检测音频；识别出所述待检测音频中的初始声音能量突变点；获取所述待检测音频的节拍信息；结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；将所述修正后的声音能量突变点映射为音乐游戏中的互动点。In the embodiment of the present application, the audio to be detected is acquired; the initial sound energy mutation point in the audio to be detected is identified; the beat information of the audio to be detected is acquired; combined with the beat information of the audio to be detected, the The initial sound energy mutation point in the audio is detected and corrected, so as to obtain the corrected sound energy mutation point; the modified sound energy mutation point is mapped to the interaction point in the music game.

因为本申请实施例可以基于待检测音频的节拍信息，对待检测音频的初始声音能量突变点进行修正，使得修正后的声音能量突变点更符合乐曲的规律，并将修正后的声音能量突变点映射为音乐游戏中的互动点，从而提升了音乐游戏中互动点的律动性。Because the embodiment of the present application can correct the initial sound energy mutation point of the audio to be detected based on the beat information of the audio to be detected, so that the corrected sound energy mutation point is more in line with the rules of the music, and the corrected sound energy mutation point is mapped It is the interaction point in the music game, thereby improving the rhythm of the interaction point in the music game.

附图说明Description of drawings

图1为本申请实施例中基于音频的游戏拍点映射方法的一个实施例示意图；1 is a schematic diagram of an embodiment of an audio-based game beat mapping method in an embodiment of the present application;

图2为本申请实施例中图1实施例步骤103的细化步骤；FIG. 2 is a refinement step ofstep 103 in the embodiment of FIG. 1 in the embodiment of the present application;

图3为本申请实施例中音乐节拍4/4拍和3/4拍中小节的结构示意图；Fig. 3 is the structural representation of the small section in themusic rhythm 4/4 beat and 3/4 beat in the embodiment of the application;

图4为本申请实施例中图1实施例步骤104的细化步骤；FIG. 4 is a refinement step ofstep 104 in the embodiment of FIG. 1 in the embodiment of the present application;

图5为本申请实施例中删除多余初始声音能量突变点前的歌曲能量包络线示意图；5 is a schematic diagram of the energy envelope of the song before deleting the excess initial sound energy mutation point in the embodiment of the application;

图6为本申请实施例中删除多余初始声音能量突变点后的歌曲能量包络线示意图；6 is a schematic diagram of the energy envelope of the song after deleting the excess initial sound energy mutation point in the embodiment of the application;

图7为本申请实施例中基于音频的游戏拍点映射方法的另一个实施例示意图；7 is a schematic diagram of another embodiment of an audio-based game beat mapping method in an embodiment of the present application;

图8为本申请实施例中基于音频的游戏拍点映射装置的一个实施例示意图。FIG. 8 is a schematic diagram of an embodiment of an audio-based game beat mapping apparatus according to an embodiment of the present application.

具体实施方式Detailed ways

本发明实施例提供了一种基于音频的游戏拍点映射方法及相关装置，用于对待检测音频的初始声音能量突变点进行修正，使得修正后的声音能量突变点更符合乐曲的规律，并将修正后的声音能量突变点映射为音乐游戏中的互动点，从而提升了音乐游戏中互动点的律动性。Embodiments of the present invention provide an audio-based game beat mapping method and a related device, which are used to correct the initial sound energy mutation point of the audio to be detected, so that the corrected sound energy mutation point is more in line with the rules of the music, and the The revised sound energy mutation point is mapped to the interaction point in the music game, thereby improving the rhythm of the interaction point in the music game.

为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments are part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third", "fourth", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that data so used can be interchanged under appropriate circumstances so that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

基于现有技术中，检测出的Onset(声音能量突变点)，容易受乐曲中的乐器、人声等因素的影响，从而使得音频中检测到的Onset较为杂乱的问题，本申请提出了一种基于音频的游戏拍点映射方法及相关装置，用于结合待检测音频的节拍信息，对待检测音频中的声音能量突变点进行修正，然后将修正后的声音能量突变点映射为音乐游戏中的互动点，从而提升音乐游戏中互动点的律动性。Based on the problem in the prior art that the detected Onset (sound energy mutation point) is easily affected by factors such as musical instruments and vocals in the music, so that the detected Onset in the audio is relatively cluttered, the present application proposes a The audio-based game beat mapping method and related device are used to modify the sound energy mutation point in the audio to be detected in combination with the beat information of the audio to be detected, and then map the corrected sound energy mutation point to the interaction in the music game points, thereby enhancing the rhythm of the interactive points in the music game.

为方便理解，下面对本申请实施例中基于音频的游戏拍点映射方法进行详细描述，请参阅图1，本申请实施例中具有音频的游戏拍点映射方法的一个实施例，包括：For the convenience of understanding, the audio-based game beat mapping method in the embodiment of the present application will be described in detail below. Please refer to FIG. 1. An embodiment of the game beat mapping method with audio in the embodiment of the present application includes:

101、获取待检测音频；101. Obtain the audio to be detected;

容易理解的是，本申请在将音频中的oneset(声音能量突变点)映射为音乐游戏中的互动点之前，需要先获取待检测音频，其中，本申请实施例中的“获取”既可以是主动获取，也可以是被动接受。It is easy to understand that, before mapping the oneset (sound energy mutation point) in the audio to the interactive point in the music game, the application needs to acquire the audio to be detected. Active acquisition can also be passive acceptance.

具体的，本申请方法的执行主体可以是各种计算机设备(如台式计算机、笔记本、平板或可穿戴设备)，以及安装在各种计算机设备中的APP或小程序等。Specifically, the execution body of the method of the present application may be various computer devices (such as desktop computers, notebooks, tablets or wearable devices), as well as APPs or small programs installed in various computer devices.

进一步，音频的Onset，也被称为音频中的声音能量突变点，指的是音频在播放的过程中，突然出现其他声音的起始点，而其他声音可以是除当前播放声音外的任一种类别的声音，如其他乐器(小提琴、鼓、钢琴)的声音，或其他合唱者的声音。Further, the Onset of the audio, also known as the sound energy mutation point in the audio, refers to the starting point where other sounds suddenly appear during the audio playback, and the other sounds can be any other than the currently playing sound. Category sounds, such as the sounds of other instruments (violin, drums, piano), or the sounds of other chorus players.

102、识别出所述待检测音频中的初始声音能量突变点；102. Identify the initial sound energy mutation point in the audio to be detected;

具体的，本申请实施例中的初始声音能量突变点指的是用传统的方法所识别出的音频中的未修正前的声音能量突变点，而传统识别音频中声音能量突变的方法有很多，可以是基于现有的音频处理工具，如Librosa工具包进行处理，或采用深度神经网络算法进行识别，此处不做具体限制。Specifically, the initial sound energy mutation point in the embodiment of the present application refers to the uncorrected sound energy mutation point in the audio frequency identified by the traditional method, and there are many traditional methods for identifying the sound energy mutation in the audio frequency. It can be processed based on existing audio processing tools, such as the Librosa toolkit, or recognized by using a deep neural network algorithm, which is not specifically limited here.

103、获取所述待检测音频的节拍信息；103. Acquire beat information of the audio to be detected;

为了对待检测音频中的初始声音能量突变点进行修正，本申请实施例中还需要获取待检测音频的节拍信息，其中，此处的节拍信息包括音频的拍点信息、重拍信息、拍型信息和单位时间内节拍数中的至少一项，此处不做具体限制。In order to correct the initial sound energy mutation point in the audio to be detected, it is also necessary to obtain beat information of the audio to be detected in this embodiment of the present application, where the beat information here includes beat information, rebeat information, and beat pattern information of the audio and at least one of the number of beats per unit time, which is not specifically limited here.

具体的，音频的拍点信息包括在音频中出现beat(节拍)的时刻，重拍信息包括出现downbeat(重拍)的时刻，拍型信息则为音频中一小节里面有多少个节拍点(beat)，如具体的拍型信息可以包括4/4拍，3/4拍等，也即一小节里可以有4个beat，或3个beat等，而单位时间内的节拍数也被称为BPM，即为单位时间内出现beat的数量。Specifically, the beat information of the audio includes the moment when a beat (beat) occurs in the audio, the rebeat information includes the moment when a downbeat (rebeat) occurs, and the beat type information is how many beat points (beats) are in a section of the audio. ), for example, the specific beat information can include 4/4 beats, 3/4 beats, etc., that is, there can be 4 beats, or 3 beats, etc. in a bar, and the number of beats per unit time is also called BPM , which is the number of beats in unit time.

104、结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；104. Modifying the initial sound energy mutation point in the to-be-detected audio in combination with the beat information of the audio to be detected, to obtain a corrected sound energy mutation point;

本申请实施例中，为了使得待检测音频中的声音能量突变点更符合乐曲的规律，故结合了待检测音频的节拍信息，对待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点。In the embodiment of the present application, in order to make the sound energy mutation point in the audio to be detected more in line with the rules of the music, the beat information of the audio to be detected is combined, and the initial sound energy mutation point in the audio to be detected is corrected to obtain the corrected The sound energy mutation point.

对于如何结合待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点的具体过程，将在下面的实施例中进行描述，此处不再赘述。The specific process of how to modify the initial sound energy mutation point in the to-be-detected audio in combination with the beat information of the audio to be detected to obtain the corrected sound energy mutation point will be described in the following embodiments. It is not repeated here.

105、将所述修正后的声音能量突变点映射为音乐游戏中的互动点。105. Map the modified sound energy mutation point to an interaction point in the music game.

为了使得音乐游戏中的互动点更符合乐曲的规律，也即更有律动性，本申请实施例将修正后的声音能量突变点映射为音乐游戏中的互动点，以用于提升音乐游戏中互动点的律动性。In order to make the interaction points in the music game more in line with the rules of the music, that is, more rhythmic, the embodiment of the present application maps the modified sound energy mutation points to the interaction points in the music game, so as to improve the interaction in the music game The rhythm of the point.

基于图1所述的实施例，当步骤102中的节拍信息为待检测音频的拍型信息时，下面对待检测音频的拍型信息的获取过程进行描述，请参阅图2，图2为图1实施例中步骤103的细化步骤：Based on the embodiment shown in FIG. 1 , when the beat information instep 102 is the beat pattern information of the audio to be detected, the following describes the acquisition process of the beat pattern information of the audio to be detected, please refer to FIG. 2 , which is FIG. 1 The refinement steps ofstep 103 in the embodiment:

201、基于信号处理或深度学习神经网络模型检测出所述待检测音频中的拍点信息和重拍信息；201. Detect beat information and rebeat information in the audio to be detected based on signal processing or a deep learning neural network model;

具体的，识别待检测音频中的拍点信息(beat)和重拍信息(downbeat)，可以有很多方法，如传统的信号处理或深度学习神经网络模型等，具体的深度学习神经网络模型可以为采用python的开源库madmom对待检测音频中的拍点信息(beat)和重拍信息(downbeat)进行检测。Specifically, there are many methods for identifying beat information (beat) and downbeat information (downbeat) in the audio to be detected, such as traditional signal processing or deep learning neural network model, etc. The specific deep learning neural network model can be The open source library madmom of python is used to detect the beat information (beat) and rebeat information (downbeat) in the audio to be detected.

202、获取所述重拍信息和所述拍点信息在所述待检测音频中的分布规律；202. Obtain the distribution rule of the rebeat information and the beat point information in the audio to be detected;

在一首歌曲中，歌曲的拍型是指在每一小节中音符的总长度，常见的歌曲拍型有1/4，2/4，3/4，4/4，3/8，6/8等，而根据歌曲的拍型不同，重拍信息和拍点信息往往遵从一定的分布规律，如在4/4拍的小节中，一般是以强拍(重拍)、弱拍、次强拍、弱拍的结构构成一个完整的小节，而在3/4拍的小节中，一般是以强拍(重拍)、弱拍、次强拍、结构构成一个完整的小节。In a song, the beat pattern of the song refers to the total length of the notes in each measure. Common song patterns are 1/4, 2/4, 3/4, 4/4, 3/8, 6/ 8, etc., and according to the different beat patterns of the song, the rebeat information and the beat information often follow a certain distribution law. The structure of beat and upbeat constitutes a complete measure, while in a measure of 3/4 time, a complete measure is generally composed of upbeat (rebeat), upbeat, sub-upbeat, and structure.

为方便理解，图3中给出了4/4拍和3/4拍中小节的结构示意图，也在图中标注了重拍信息和拍点信息所遵从的分布规律。For the convenience of understanding, FIG. 3 shows a schematic diagram of the structure of the subsections in 4/4 beat and 3/4 beat, and the distribution rules complied with by the rebeat information and the beat point information are also marked in the figure.

203、根据所述分布规律，获取所述待检测音频的拍型信息。203. Acquire beat pattern information of the audio to be detected according to the distribution rule.

具体如步骤202所述，因为在4/4拍的小节中，一般是以强拍(重拍)、弱拍、次强拍、弱拍的结构构成一个完整的小节，而在3/4拍的小节中，一般是以强拍(重拍)、弱拍、次强拍的结构构成一个完整的小节，故在识别出待检测音频中重拍信息和拍点信息的分布规律后，即可根据待检测音频中重拍信息和拍点信息的分布规律，获取待检测音频的拍型信息。Specifically, as described instep 202, because in a measure of 4/4 beat, a complete measure is generally composed of the structure of upbeat (rebeat), upbeat, sub-upbeat, and upbeat, while in 3/4 beat In the sub-sections, a complete section is generally composed of strong beats (rebeats), upbeats, and sub-strong beats. According to the distribution rule of the rebeat information and the beat information in the audio to be detected, the beat pattern information of the audio to be detected is acquired.

本申请实施例中给出了获取待检测音频拍型信息的具体过程，提升了识别待检测音频的拍型信息过程的可靠性。The embodiment of the present application provides a specific process for acquiring the beat pattern information of the audio to be detected, which improves the reliability of the process of identifying the beat pattern information of the audio to be detected.

基于图1和图2所述的实施例，下面接着对图1实施例中的步骤104做详细描述，请参阅图4，图4为图1实施例中步骤104的细化步骤：Based on the embodiments described in FIG. 1 and FIG. 2 , the following is a detailed description ofstep 104 in the embodiment of FIG. 1 , please refer to FIG. 4 , which is a refinement step ofstep 104 in the embodiment of FIG. 1 :

401、根据所述待检测音频的拍型信息和单位时间内的节拍数，计算所述初始声音能量突变点出现的最小时间间隔；401. According to the beat pattern information of the audio to be detected and the beat number per unit time, calculate the minimum time interval at which the initial sound energy mutation point occurs;

具体的，本申请实施例中待检测音频的节拍信息包括待检测音频的拍型信息和单位时间内的节拍数。其中，待检测音频在单位时间内的节拍数可以通过用python的开源库madmom进行检测。Specifically, the beat information of the audio to be detected in the embodiment of the present application includes the beat pattern information of the audio to be detected and the number of beats per unit time. Among them, the number of beats of the audio to be detected per unit time can be detected by using the python open source library madmom.

而在图2实施例中获取待检测音频的拍型信息后，则可以根据待检测音频的拍型信息和单位时间内的节拍数，计算待检测音频中初始声音能量突变点出现的最小时间间隔。In the embodiment of FIG. 2 , after obtaining the beat pattern information of the audio to be detected, the minimum time interval for the occurrence of the initial sound energy mutation point in the audio to be detected can be calculated according to the beat pattern information of the audio to be detected and the number of beats per unit time. .

为方便理解，下面举例说明：For ease of understanding, the following examples illustrate:

假设待检测音频的BPM(单位时间1s内的节拍数)为87，而待检测音频的拍型为4/4拍，则初始声音能量突变点出现的最小时间间隔为

Assuming that the BPM (number of beats per unit time 1s) of the audio to be detected is 87, and the beat pattern of the audio to be detected is 4/4 beats, the minimum time interval for the initial sound energy mutation point to appear is

需要说的是，本申请实施例是以4/4拍进行举例说明，而当待检测音频为3/4拍，则初始声音能量突变点出现的最小时间间隔为

也即本申请实施例初始声音能量突变点出现的最小时间间隔关联于待检测音频的拍型信息。It should be noted that the embodiment of the present application uses 4/4 beats as an example, and when the to-be-detected audio frequency is 3/4 beats, the minimum time interval for the initial sound energy mutation point to appear is

That is, the minimum time interval at which the initial sound energy sudden change point appears in the embodiment of the present application is associated with the beat pattern information of the audio to be detected.

402、判断在不大于所述最小时间间隔一半的时间内，是否出现多个初始声音能量突变点，若是，则执行步骤403，若否，则执行步骤404；402. Determine whether there are multiple initial sound energy mutation points within a time not greater than half of the minimum time interval, if so, go to step 403, if not, go to step 404;

步骤401中获取到待检测音频中初始声音能量突变点出现的最小时间间隔后，进一步判断在不大于所述最小时间间隔一半的时间内，是否出现多个初始声音能量突变点，其中，本申请实施例中的多个为至少2个，并在若是时，执行步骤403，而在若否时，执行步骤404.Instep 401, after obtaining the minimum time interval for the occurrence of the initial sound energy mutation point in the audio to be detected, it is further judged whether there are multiple initial sound energy mutation points within a time not greater than half of the minimum time interval. The plurality in the embodiment is at least 2, and if yes, executestep 403, and if not, executestep 404.

403、若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作和/或调整操作，以得到修正后的声音能量突变点；403. If multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, perform a deletion operation and/or an adjustment operation on the multiple initial sound energy mutation points, so as to obtain the corrected sound energy. The sound energy mutation point;

若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作和/或调整操作，以得到修正后的声音能量突变点；If multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, perform a deletion operation and/or an adjustment operation on the multiple initial sound energy mutation points to obtain a modified sound energy mutation point;

具体的，对所述多个初始声音能量突变点执行删减操作包括：Specifically, performing the pruning operation on the multiple initial sound energy mutation points includes:

1、若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则将所述多个初始声音能量突变点中的至少两个初始声量突变点合并为一个初始声音能量突变点。1. If multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, at least two initial sound volume mutation points in the multiple initial sound energy mutation points are combined into one initial sound. Energy mutation point.

为保持描述的一致性，此处延续步骤401中的4/4拍进行举例说明：假设在最小时间间隔0.1724s内，出现了多个(大于等于2个)初始声音能量突变点，则将所述多个初始声音能量突变点中的至少两个初始声音能量突变点合并为一个初始声音能量突变点。In order to maintain the consistency of the description, the 4/4 beat instep 401 is continued as an example for illustration: assuming that within the minimum time interval of 0.1724s, there are multiple (greater than or equal to 2) initial sound energy mutation points, all At least two initial sound energy mutation points among the plurality of initial sound energy mutation points are merged into one initial sound energy mutation point.

也即假设在最小时间间隔0.1724s内，出现了3个初始声音能量突变点，则将3个初始声音能量突变点中的至少2个合并为1个初始声音能量突变点，使得在最小时间间隔0.1724s内至少保持1个初始声音能量突变点。That is to say, assuming that there are 3 initial sound energy mutation points within the minimum time interval of 0.1724s, at least 2 of the 3 initial sound energy mutation points are merged into one initial sound energy mutation point, so that in the minimum time interval Keep at least one initial sound energy mutation point within 0.1724s.

2、根据所述待检测音频的拍型信息，获取待检测音频相邻拍点内允许出现声音能量突变点的最大数量；判断在待检测音频相邻拍点内出现初始声音能量突变点的数量是否大于所述最大数量，若是，则删除最大数量以外的其他初始声音能量突变点，若否，则保持所述相邻拍点内出现初始声音能量突变点的数量，并获取该数量初始声音能量突变点所在相邻拍点间的时间段，将所述相邻拍点内的初始声音能量突变点的数量均分至相邻拍点间时间段内的各个时刻。2. According to the beat pattern information of the audio to be detected, obtain the maximum number of sound energy mutation points that are allowed to appear in the adjacent beats of the audio to be detected; determine the number of initial sound energy mutation points that appear in the adjacent beats of the audio to be detected Whether it is greater than the maximum number, if so, delete other initial sound energy mutation points other than the maximum number, if not, keep the number of initial sound energy mutation points in the adjacent beat points, and obtain the number of initial sound energy For the time period between adjacent beat points where the mutation point is located, the number of initial sound energy mutation points in the adjacent beat points is equally divided into each moment in the time period between adjacent beat points.

在将所述多个初始声音能量突变点中的至少两个初始声音能量突变点合并为一个初始声音能量突变点后，为了进一步使得初始声音能量突变点更符合乐理规律，本申请实施例还进一步根据所述待检测音频的拍型信息，获取待检测音频相邻拍点内允许出现声音能量突变点的最大数量，其中，待检测音频相邻拍点内允许出现声音能量突变点的最大数量如下所述：After merging at least two initial sound energy mutation points of the plurality of initial sound energy mutation points into one initial sound energy mutation point, in order to further make the initial sound energy mutation point more in line with the laws of music theory, the embodiments of the present application further According to the beat pattern information of the audio to be detected, obtain the maximum number of sound energy mutation points allowed in adjacent beats of the audio to be detected, wherein the maximum number of allowed sound energy mutation points in the adjacent beats of the audio to be detected is as follows Said:

若待检测音频为4/4拍，则待检测音频相邻拍点内允许出现声音能量突变点的最大数量为4-1＝3，若待检测音频为3/4拍，则待检测音频相邻拍点内允许出现声音能量突变点的最大数量为3-1＝2。If the to-be-detected audio is 4/4 beats, the maximum number of sound energy mutation points allowed in adjacent beats of the to-be-detected audio is 4-1=3; if the to-be-detected audio is 3/4 beats, then the The maximum number of sound energy mutation points allowed in adjacent beat points is 3-1=2.

若在将所述多个初始声音能量突变点中的至少两个初始声量突变点合并为一个初始声音能量突变点以后，在待检测音频相邻拍点内出现初始声音能量突变点的数量大于所述最大数量，则删除所述最大数量以外的其他初始声音能量突变点。If at least two initial sound energy mutation points in the plurality of initial sound energy mutation points are combined into one initial sound energy mutation point, the number of initial sound energy mutation points in adjacent beat points of the audio to be detected is greater than all the initial sound energy mutation points. If the maximum number is specified, other initial sound energy mutation points other than the maximum number are deleted.

下面举例说明：The following examples illustrate:

假设在将所述多个初始声音能量突变点中的至少两个初始声量突变点合并为一个初始声音能量突变点以后，在最小时间间隔0.2299s内出现了3个初始声音能量突变点，而待检测音频相邻拍点内允许出现声音能量突变点的最大数量为2，则删除最大数量(2个)以外的其他(1个)初始声音能量突变点。It is assumed that after combining at least two initial sound energy mutation points of the multiple initial sound energy mutation points into one initial sound energy mutation point, 3 initial sound energy mutation points appear within the minimum time interval of 0.2299s. The maximum number of sound energy mutation points allowed in the adjacent beat points of the detected audio is 2, and other (1) initial sound energy mutation points other than the maximum number (2) are deleted.

具体的，在删除最大数量(2个)以外的其他(1个)初始声音能量突变点时，可以是随机删除1个初始声音能量突变点，也可以是删除初始声音能量突变点中能量最弱的那个点，此处对删除的方式不做具体限制。Specifically, when deleting other (1) initial sound energy mutation points other than the maximum number (2), one initial sound energy mutation point can be deleted randomly, or the weakest energy among the initial sound energy mutation points can be deleted. At that point, there is no specific restriction on the deletion method here.

为方便理解，图5和图6分别给出了删除多余初始声音能量突变点前后的歌曲能量包络线示意图。For ease of understanding, FIG. 5 and FIG. 6 respectively show the schematic diagrams of the energy envelope of the song before and after deleting the excess initial sound energy mutation point.

而若在将所述多个初始声音能量突变点中的至少两个初始声量突变点合并为一个初始声音能量突变点以后，在待检测音频相邻拍点内出现初始声音能量突变点的数量不大于所述最大数量，则保持相邻拍点内出现初始声音能量突变点的数量，并获取该数量初始声音能量突变点所在相邻拍点间的时间段，将相邻拍点内的初始声音能量突变点的数量均分至相邻拍点间时间段内的各个时刻，以提升初始声音能量突变点分布的规律性。However, if at least two of the multiple initial sound energy mutation points are merged into one initial sound energy mutation point, the number of initial sound energy mutation points in the adjacent beats of the audio to be detected is different. If it is greater than the maximum number, then keep the number of initial sound energy mutation points in adjacent beat points, and obtain the time period between adjacent beat points where the initial sound energy mutation point of this number is located, and use the initial sound energy in adjacent beat points. The number of energy mutation points is evenly divided into each moment in the time period between adjacent beats to improve the regularity of the distribution of initial sound energy mutation points.

3、获取所述最大数量的初始声音能量突变点所在相邻拍点间的时间段；将所述最大数量的初始声音能量突变点均分至所述时间段内的各个时刻。3. Obtain the time period between the adjacent beats where the maximum number of initial sound energy mutation points are located; and equally divide the maximum number of initial sound energy mutation points into each moment in the time period.

在删除所述最大数量以外的其他初始声音能量突变点以后，为了进一步提升声音能量突变点分布的规律性，本申请实施例还进一步获取最大数量的初始声音能量突变点所在相邻拍点间的时间段，并将所述最大数量的初始声音能量突变点均分至所述时间段内的各个时刻。After deleting other initial sound energy mutation points other than the maximum number, in order to further improve the regularity of the distribution of sound energy mutation points, the embodiment of the present application further obtains the maximum number of initial sound energy mutation points between adjacent beats. time period, and equally divide the maximum number of initial sound energy mutation points into each moment in the time period.

下面结合图6进行说明，假设在位于x1时刻和x2时刻的拍点内出现了2个(最大数量)声音能量突变点，则将位于x1时刻和x2时刻之间的2个声音能量突变点(最大数量声音能量突变点)均分至x1时刻和x2时刻之间，如将第一个声音能量突变点设置于x1+(x2-x1)/3的时刻，而将第二个声音能量突变点设置于x1+2(x2-x1)/3的时刻。The following description will be given in conjunction with Fig. 6. Assuming that there are 2 (maximum number) sound energy mutation points in the beats located at time x1 and time x2, then the 2 sound energy mutation points located between time x1 and time x2 ( The maximum number of sound energy mutation points) is evenly divided between x1 time and x2 time. For example, the first sound energy mutation point is set at the moment of x1+(x2-x1)/3, and the second sound energy mutation point is set At the moment of x1+2(x2-x1)/3.

404、若在不大于所述最小时间间隔一半的时间内，出现一个初始声音能量突变点，则保持所述单个初始声音能量突变点，并获取单个初始声音能量突变点所在相邻拍点间的时间段，将所述单个初始声音能量突变点均分至所述单个初始声音能量突变点所在相邻拍点间的时间段内，以得到修正后的声音能量突变点。404. If an initial sound energy mutation point occurs within a time not greater than half of the minimum time interval, keep the single initial sound energy mutation point, and obtain the difference between adjacent beats where the single initial sound energy mutation point is located. Time period, the single initial sound energy mutation point is equally divided into the time period between the adjacent beat points where the single initial sound energy mutation point is located, so as to obtain the corrected sound energy mutation point.

若在不大于所述最小时间间隔一半的时间内，只出现一个初始声音能量突变点，则对该初始声音能量突变点不做任何处理，也即保持所述初始声音能量突变点，并将该单个初始声音能量突变点均分至所述单个初始声音能量突变点所在相邻拍点间的时间段内。If there is only one initial sound energy mutation point within a time not greater than half of the minimum time interval, no processing is performed on the initial sound energy mutation point, that is, the initial sound energy mutation point is maintained, and the A single initial sound energy mutation point is equally divided into a time period between adjacent beat points where the single initial sound energy mutation point is located.

下面举例说明：The following examples illustrate:

假设在位于x1时刻和x2时刻的拍点内只出现了1个声音能量突变点，则直接将该单个声音能量突变点设置于(x2-x1)/2的时刻。Assuming that there is only one sound energy mutation point in the beats located at time x1 and time x2, the single sound energy mutation point is directly set at the moment of (x2-x1)/2.

本申请实施例中，对结合所述待检测音频的节拍信息，对所述待检测音频中的声音能量突变点进行修正，以得到修正后的声音能量突变点的具体过程做了详细描述，从而提升了本申请获取修改正声音能量突变点过程的可靠性，且使得修正后的声音能量突变点更符合乐理规律。In the embodiment of the present application, the specific process of modifying the sound energy mutation point in the to-be-detected audio frequency in combination with the beat information of the to-be-detected audio frequency to obtain the corrected sound energy mutation point is described in detail. The reliability of the process of obtaining and modifying the positive sound energy mutation point of the present application is improved, and the corrected sound energy mutation point is more in line with the laws of music theory.

下面结合上述实施例，对本申请实施例中基于音频的游戏拍点映射方法做详细描述，请参阅图7，图7为本申请实施例中基于音频的游戏拍点映射方法的另一个实施例：Below in conjunction with the foregoing embodiments, the audio-based game beat mapping method in the embodiment of the present application is described in detail, please refer to FIG. 7 , and FIG. 7 is another embodiment of the audio-based game beat mapping method in the embodiment of the present application:

701、获取待检测音频；701. Obtain the audio to be detected;

需要说明的是，本申请实施例中的步骤701与图1实施例中的101的描述类似，此处不再赘述。It should be noted thatstep 701 in this embodiment of the present application is similar to the description ofstep 101 in the embodiment of FIG. 1 , and details are not repeated here.

702、对所述待检测音频执行预处理，以减少所述待检测音频的数据处理量，其中，所述预处理包括将所述待检测音频转换为单声道语音信号和将所述待检测音频的采样率重采样至标准采样率中的至少一项；702. Perform preprocessing on the to-be-detected audio to reduce the data processing amount of the to-be-detected audio, wherein the pre-processing includes converting the to-be-detected audio into a monophonic voice signal and converting the to-be-detected audio The sampling rate of the audio is resampled to at least one of the standard sampling rates;

本申请实施例在获取到待检测音频后，为了减少音频运算的数据量，从而减轻计算压力以提升运算效率，还可以对待检测音频执行预处理，以减少对待检测音频的数据处理量，其中，预处理包括将待检测音频转换为单声道语音信号和将待检测音频的采样率重采样至标准采样率中的至少一项。After the audio to be detected is acquired in the embodiment of the present application, in order to reduce the data volume of the audio operation, thereby reducing the calculation pressure and improving the operation efficiency, preprocessing of the audio to be detected may also be performed, so as to reduce the data processing amount of the audio to be detected, wherein, The preprocessing includes at least one of converting the audio to be detected into a monophonic speech signal and resampling the sampling rate of the audio to be detected to a standard sampling rate.

具体的，在获取到待检测音频后，若待检测音频为非单声道信号，则可以将待检测音频转换为单声道语音信号，如待检测音频为双声道信号，因为双声道信号为在双声道中输出完全一样的波形信号，故可以通过平均两个声道的信号能量从而得到单声道信号。Specifically, after acquiring the audio to be detected, if the audio to be detected is a non-monaural signal, the audio to be detected can be converted into a monophonic voice signal, for example, the audio to be detected is a dual-channel signal, because the dual-channel audio The signal is exactly the same waveform signal output in the two channels, so the mono signal can be obtained by averaging the signal energy of the two channels.

而若待检测音频的采样率高于预设的标准采样率(如高于8kHz)，则可以将该音频信号重采样至标准采样率(如8kHz)。具体的，在对音频信号重采样时，可以是开源工具(libresample)或者直接进行序列抽取等操作来实现音频信号的重采样。If the sampling rate of the audio to be detected is higher than the preset standard sampling rate (eg, higher than 8 kHz), the audio signal can be resampled to the standard sampling rate (eg, 8 kHz). Specifically, when resampling the audio signal, an open source tool (libresample) or directly performing operations such as sequence extraction can be used to implement the resampling of the audio signal.

需要说明的是，此处的8kHz只是对预设的标准采样率进行举例说明，而非具体限制，此处对预设的标准采样率不做具体限制，如预设的标准采样率可以是44100Hz，或48000Hz，或96000Hz等。It should be noted that 8kHz here is only an example of the preset standard sampling rate, not a specific limitation. There is no specific restriction on the preset standard sampling rate here. For example, the preset standard sampling rate can be 44100Hz. , or 48000Hz, or 96000Hz, etc.

703、识别出所述待检测音频中的初始声音能量突变点；703. Identify the initial sound energy mutation point in the audio to be detected;

704、获取所述待检测音频的节拍信息；704. Acquire beat information of the audio to be detected;

需要说明的是，本申请实施例中的步骤703和704与图1实施例中的102至103的描述类似，此处不再赘述。It should be noted that, steps 703 and 704 in this embodiment of the present application are similar to the descriptions of 102 to 103 in the embodiment of FIG. 1 , and are not repeated here.

705、待检测音频的节拍信息包括待检测音频的拍型信息和单位时间内的节拍数，根据所述待检测音频的拍型信息和单位时间内的节拍数，计算所述初始声音能量突变点出现的最小时间间隔；705. The beat information of the audio to be detected includes the beat pattern information of the audio to be detected and the number of beats per unit time, and the initial sound energy mutation point is calculated according to the beat pattern information of the audio to be detected and the number of beats per unit time. the minimum time interval between occurrences;

706、判断在不大于所述最小时间间隔一半的时间内，是否出现多个初始声音能量突变点，若是，则执行步骤707，若否，则执行步骤708；706. Determine whether there are multiple initial sound energy mutation points within a time not greater than half of the minimum time interval, if so, executestep 707, if not, executestep 708;

707、若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作和/或调整操作，以得到修正后的声音能量突变点；707. If multiple initial sound energy mutation points occur within a time period not greater than half of the minimum time interval, perform a deletion operation and/or an adjustment operation on the multiple initial sound energy mutation points to obtain the corrected sound energy. The sound energy mutation point;

708、若在不大于所述最小时间间隔一半的时间内，出现一个初始声音能量突变点，则保持所述初始声音能量突变点，并获取单个初始声音能量突变点所在相邻拍点间的时间段，将所述单个初始声音能量突变点均分至所述单个初始声音能量突变点所在相邻拍点间的时间段内，以得到修正后的声音能量突变点；708. If an initial sound energy mutation point occurs within a time not greater than half of the minimum time interval, keep the initial sound energy mutation point, and obtain the time between adjacent beats where the single initial sound energy mutation point is located. segment, the single initial sound energy mutation point is equally divided into the time period between the adjacent beat points where the single initial sound energy mutation point is located, so as to obtain the corrected sound energy mutation point;

709、识别出所述待检测音频中的拍点信息、重拍信息和长拍信息中的至少一项；709. Identify at least one item of beat information, rebeat information, and long beat information in the audio to be detected;

具体的，在识别待检测音频中的拍点信息、重拍信息时，可以是基于传统信号处理的方式，或基于深度学习神经网络模型来进行识别，如采用如开源库madmom中有DBNDownBeatTrackingProcessor算法来进行识别。Specifically, when identifying the beat information and rebeat information in the audio to be detected, it can be based on traditional signal processing, or based on a deep learning neural network model. to identify.

进一步，在识别待检测音频中的长拍信息时，可以基于以下方式进行识别：Further, when identifying the long-beat information in the audio to be detected, the identification can be performed based on the following methods:

对输入的歌词文件或midi文件(其中，歌词文件或midi文件会显示每个歌词或每个音符的起始时刻和持续时长)，获取所述待检测音频中每个音符和/或每个歌词的起始时刻和持续时长；将持续时长大于第一预设时长的音符和/或歌词，确定为所述待检测音频中的长拍信息。For the input lyric file or midi file (wherein the lyric file or midi file will display the start time and duration of each lyric or each note), obtain each note and/or each lyric in the audio to be detected The starting time and duration; the notes and/or lyrics whose duration is longer than the first preset duration are determined as the long beat information in the audio to be detected.

如《lemom》最后一句歌词为：For example, the last line of "lemom" reads:

今(238391,284)で(238675,330)も(239005,303)あ(239308,278)な(239586,294)た(239880,415)は(240295,313)わ(240608,318)た(240926,328)し(241254,376)の(241630,395)光(242025,2663)。Today(238391,284)で(238675,330)も(239005,303)あ(239308,278)な(239586,294)た(239880,415)は(240295,313)わ(240608,318)た( 240926,328)し(241254,376)の(241630,395) Light (242025,2663).

其中，歌词后的第一个时间点为歌词的开始时刻(单位为ms)，第二个时间为歌词的持续时长(单位为ms)，如今(238391,284)中，238391为“今”开始的时刻点，而284为“今”的持续时长。Among them, the first time point after the lyrics is the start time of the lyrics (unit is ms), the second time is the duration of the lyrics (unit is ms), and now (238391, 284), 238391 is the beginning of "now" , and 284 is the duration of "today".

假设该首歌中，第一预设时长为0.51724s，则《lemom》最后一句歌词中，只有“光”为长拍。Assuming that the first preset duration in this song is 0.51724s, in the last lyric of "lemom", only "light" is a long beat.

710、依次标记出所述待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点；710. Mark the long beat information, the rebeat information, the beat point information, and the corrected sound energy mutation point in the audio to be detected in sequence;

在识别出待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点后，然后依次标记出待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点，并在标记的过程中执行步骤712。After identifying the long beat information, rebeat information, beat point information and the corrected sound energy mutation point in the audio to be detected, then mark the long beat information, rebeat information, beat point information and The corrected sound energy mutation point, and step 712 is performed during the marking process.

711、判断修正后的声音能量突变点与所述重拍信息和/或所述拍点信息是否重叠，若是，则执行步骤712，若否，则执行步骤713。711. Determine whether the corrected sound energy mutation point overlaps with the rebeat information and/or the beat information, if so, go to step 712, and if not, go to step 713.

为了增强待检测音频的律动性，在依次标记出待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点的过程中，判断修正后的声音能量突变点与所述重拍信息和/或所述拍点信息是否重叠，若是，则执行步骤712，若否，则执行步骤713。In order to enhance the rhythm of the audio to be detected, in the process of sequentially marking the long-beat information, re-beat information, beat information and the modified sound energy mutation point in the audio to be detected, determine the difference between the corrected sound energy mutation point and the sound energy mutation point. Whether the retake information and/or the beat information overlap, if yes, go to step 712 , if not, go to step 713 .

712、若修正后的声音能量突变点与所述重拍信息和/或所述拍点信息重叠，则将所述修正后的声音能量突变点标记为所述重拍信息和/或所述拍点信息。712. If the modified sound energy mutation point overlaps with the rebeat information and/or the beat information, mark the corrected sound energy mutation point as the rebeat information and/or the beat information. point information.

若修正后的声音能量突变点与所述重拍信息和/或所述拍点信息重叠，为了增强待检测音频的律动性，则将修正后的声音能量突变点对应标记为所述重拍信息和/或所述拍点信息。If the corrected sound energy mutation point overlaps with the rebeat information and/or the beat information, in order to enhance the rhythm of the audio to be detected, the corrected sound energy mutation point is correspondingly marked as the rebeat information and/or the beat information.

713、将所述待检测音频中修正后的声音能量突变点，和拍点信息、重拍信息与长拍信息中的至少一项映射为音乐游戏中的互动点。713. Map the corrected sound energy mutation point in the audio to be detected, and at least one item of beat information, rebeat information, and long beat information as interactive points in the music game.

作为一种可能的实施方式，在映射的过程中，可以是将待检测音频中的拍点信息和声音能量突变点映射为音乐游戏中的单击，将待检测音频中的重拍信息映射为音乐游戏中的双击，将待检测音频中的长拍映射为音乐游戏中预设时长的连续按压。As a possible implementation, during the mapping process, the beat information and the sound energy mutation point in the audio to be detected may be mapped to a click in the music game, and the rebeat information in the audio to be detected may be mapped to A double-click in a music game maps a long beat in the audio to be detected to a preset duration of continuous pressing in the music game.

除此以外，根据实际应用场景，还可以以其他方式将待检测音频中的拍点信息、重拍信息、长拍信息和声音能量突变点，映射为音乐游戏中的互动点，如将待检测音频中的拍点信息映射为音乐游戏中的双击，将待检测音频中的重拍信息映射为音乐游戏中的重击，将待检测音频中的长拍信息映射为音乐游戏中的N连拍，将待检测音频中的声音能量突变点映射为音乐游戏中的单击等，此处对将待检测音频中拍点信息、重拍信息、长拍信息和声音能量突变点，映射为音乐游戏中的互动点的具体方式不做限制。In addition, according to the actual application scenario, beat point information, rebeat information, long beat information and sound energy mutation points in the audio to be detected can also be mapped to interactive points in the music game in other ways, such as mapping the to-be-detected audio The beat information in the audio is mapped to the double-click in the music game, the rebeat information in the audio to be detected is mapped to the heavy hit in the music game, and the long-beat information in the audio to be detected is mapped to the N continuous shooting in the music game , map the sound energy mutation point in the audio to be detected as a click in the music game, etc. Here, map the beat information, rebeat information, long beat information and sound energy mutation point in the audio to be detected to the music game There is no restriction on the specific way of interaction points in the .

本申请实施例中对待检测音频的预处理过程做了详细描述，提升了对待处理音频的运算效率，对获取待检测音频中的长拍信息、重拍信息、拍点信息的过程，以及将待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点映射为音乐游戏互动点的过程做了详细描述，分别提升了各个过程的可靠性。In the embodiment of the present application, the preprocessing process of the audio to be detected is described in detail, which improves the operation efficiency of the audio to be processed. The process of detecting the long beat information, rebeat information, beat point information and the corrected sound energy mutation point mapping in the audio to the music game interaction point is described in detail, which improves the reliability of each process.

上面对本申请中基于音频的游戏拍点映射方法做了详细描述，下面接着对本申请实施例中基于音频的游戏拍点映射装置进行描述，请参阅图8，本申请实施例中基于音频的游戏拍点映射装置的一个实施例，包括：The audio-based game beat mapping method in the present application has been described in detail above. Next, the audio-based game beat mapping device in the embodiment of the present application is described. Please refer to FIG. 8 . An embodiment of a point mapping device, comprising:

获取单元801，用于获取待检测音频；anacquisition unit 801, configured to acquire audio to be detected;

识别单元802，用于识别出所述待检测音频中的初始声音能量突变点；Anidentification unit 802, configured to identify an initial sound energy mutation point in the audio to be detected;

所述获取单元801，还用于获取所述待检测音频的节拍信息；The obtainingunit 801 is further configured to obtain beat information of the audio to be detected;

修正单元803，用于结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；Amodification unit 803, configured to modify the initial sound energy mutation point in the to-be-detected audio in combination with the beat information of the audio to be detected, so as to obtain a corrected sound energy mutation point;

映射单元804，用于将所述修正后的声音能量突变点映射为音乐游戏中的互动点。Themapping unit 804 is configured to map the modified sound energy mutation point to the interaction point in the music game.

可选的，所述获取单元801具体用于：Optionally, the obtainingunit 801 is specifically used for:

所述修正单元803具体用于：Thecorrection unit 803 is specifically used for:

可选的，所述修正单元803具体用于：Optionally, thecorrection unit 803 is specifically used for:

可选的，所述修正单元803具还用于：Optionally, thecorrection unit 803 is also used for:

可选的，识别单元802，还用于识别出所述待检测音频中的拍点信息、重拍信息和长拍信息中的至少一项；Optionally, the identifyingunit 802 is further configured to identify at least one of beat information, rebeat information and long beat information in the audio to be detected;

所述映射单元804，还用于：Themapping unit 804 is also used for:

可选的，所述识别单元802具体用于：Optionally, the identifyingunit 802 is specifically used for:

可选的，所述装置还包括：Optionally, the device further includes:

标记单元805，用于在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，依次标记出所述待检测音频中的长拍信息、重拍信息、拍点信息和修正后的声音能量突变点；The markingunit 805 is used to map the modified sound energy mutation point in the audio to be detected and at least one of the beat point information, rebeat information and long beat information as interactive points in the music game , and sequentially mark the long beat information, rebeat information, beat point information and the corrected sound energy mutation point in the audio to be detected;

所述标记单元805，还用于若所述修正后的声音能量突变点与所述重拍信息和/或所述拍点信息重叠，则将所述修正后的声音能量突变点标记为所述重拍信息和/或所述拍点信息。The markingunit 805 is further configured to mark the modified sound energy mutation point as the modified sound energy mutation point if the modified sound energy mutation point overlaps with the rebeat information and/or the beat point information. Retake information and/or the beat information.

可选的，所述映射单元804具体用于：Optionally, themapping unit 804 is specifically used for:

可选的，所述装置还包括：Optionally, the device further includes:

预处理单元806，用于在识别出所述待检测音频中的初始声音能量突变点之前，对所述待检测音频执行预处理，以减少所述待检测音频的数据处理量，其中，所述预处理包括将所述待检测音频转换为单声道语音信号和将所述待检测音频的采样率重采样至标准采样率中的至少一项。Apreprocessing unit 806, configured to perform preprocessing on the to-be-detected audio before identifying the initial sound energy mutation point in the to-be-detected audio, so as to reduce the data processing amount of the to-be-detected audio, wherein the The preprocessing includes at least one of converting the audio to be detected into a monophonic speech signal and resampling the sampling rate of the audio to be detected to a standard sampling rate.

本申请实施例中，通过获取单元801获取待检测音频；通过识别单元802识别出所述待检测音频中的初始声音能量突变点；获取所述待检测音频的节拍信息；通过修正单元803结合所述待检测音频的节拍信息，对所述待检测音频中的初始声音能量突变点进行修正，以得到修正后的声音能量突变点；通过映射单元804将所述修正后的声音能量突变点映射为音乐游戏中的互动点。In the embodiment of the present application, the audio to be detected is acquired by the acquiringunit 801; the initial sound energy mutation point in the audio to be detected is identified by theidentification unit 802; the beat information of the audio to be detected is acquired; The beat information of the audio to be detected is modified, and the initial sound energy mutation point in the audio to be detected is corrected to obtain the corrected sound energy mutation point; the modified sound energy mutation point is mapped by themapping unit 804 as Interactive points in music games.

上面从模块化功能实体的角度对本发明实施例中基于音频的游戏拍点计算装置的进行了描述，下面从硬件处理的角度对本发明实施例中的计算机装置进行描述：The audio-based game beat calculation device in the embodiment of the present invention is described above from the perspective of modular functional entities, and the computer device in the embodiment of the present invention is described below from the perspective of hardware processing:

该计算机装置用于实现网关设备一侧的功能，本发明实施例中计算机装置一个实施例包括：The computer device is used to implement a function on the side of the gateway device, and an embodiment of the computer device in the embodiment of the present invention includes:

处理器以及存储器；processor and memory;

存储器用于存储计算机程序，处理器用于执行存储器中存储的计算机程序时，可以实现如下步骤：The memory is used to store the computer program, and when the processor is used to execute the computer program stored in the memory, the following steps can be implemented:

获取待检测音频；Get the audio to be detected;

在本发明的一些实施例中，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, the processor may also be used to implement the following steps:

在本发明的一些实施例中，所述节拍信息包括所述拍型信息和单位时间内的节拍数，处理器，还可以具体用于实现如下步骤：In some embodiments of the present invention, the beat information includes the beat pattern information and the beat number per unit time, and the processor can also be specifically configured to implement the following steps:

在本发明的一些实施例中，处理器，还可以具体用于实现如下步骤：In some embodiments of the present invention, the processor may also be specifically configured to implement the following steps:

在本发明的一些实施例中，在将所述多个声音能量突变点中的至少两个声音能量突变点合并为一个声音能量突变点之后，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, after combining at least two of the plurality of sound energy mutation points into one sound energy mutation point, the processor may be further configured to implement the following steps:

在本发明的一些实施例中，在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, the modified sound energy mutation point in the audio to be detected and at least one of the beat information, the rebeat information and the long beat information are mapped to the sound energy in the music game. Before the interaction point, the processor can also be used to implement the following steps:

在本发明的一些实施例中，在识别出所述待检测音频中的初始声音能量突变点之前，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, before identifying the initial sound energy mutation point in the audio to be detected, the processor may be further configured to implement the following steps:

可以理解的是，上述说明的计算机装置中的处理器执行所述计算机程序时，也可以实现上述对应的各装置实施例中各单元的功能，此处不再赘述。示例性的，所述计算机程序可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器中，并由所述处理器执行，以完成本发明。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述基于音频的游戏拍点计算装置中的执行过程。例如，所述计算机程序可以被分割成上述基于音频的游戏拍点计算装置中的各单元，各单元可以实现如上述相应基于音频的游戏拍点计算装置说明的具体功能。It can be understood that, when the processor in the computer device described above executes the computer program, the functions of the units in the corresponding device embodiments described above can also be implemented, which will not be repeated here. Exemplarily, the computer program may be divided into one or more modules/units, and the one or more modules/units are stored in the memory and executed by the processor to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the audio-based game beat calculation device. For example, the computer program may be divided into units in the above-mentioned audio-based game beat calculation apparatus, and each unit may implement the specific functions described in the above-mentioned corresponding audio-based game beat calculation apparatus.

所述计算机装置可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述计算机装置可包括但不仅限于处理器、存储器。本领域技术人员可以理解，处理器、存储器仅仅是计算机装置的示例，并不构成对计算机装置的限定，可以包括更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述计算机装置还可以包括输入输出设备、网络接入设备、总线等。The computer device may be a computing device such as a desktop computer, a notebook computer, a palmtop computer, and a cloud server. The computer device may include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the processor and the memory are only examples of the computer device, and do not constitute a limitation on the computer device, and may include more or less components, or combine certain components, or different components, such as all The computer apparatus may also include input and output devices, network access devices, buses, and the like.

所述处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable GateArray，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，所述处理器是所述计算机装置的控制中心，利用各种接口和线路连接整个计算机装置的各个部分。The processor may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf processor Programmable Gate Array (Field-Programmable GateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

所述存储器可用于存储所述计算机程序和/或模块，所述处理器通过运行或执行存储在所述存储器内的计算机程序和/或模块，以及调用存储在存储器内的数据，实现所述计算机装置的各种功能。所述存储器可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序等；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(SecureDigital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。The memory can be used to store the computer program and/or module, and the processor implements the computer by running or executing the computer program and/or module stored in the memory and calling the data stored in the memory various functions of the device. The memory may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the terminal, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, internal memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

本发明还提供了一种计算机可读存储介质，该计算机可读存储介质用于实现基于音频的游戏拍点计算装置的功能，其上存储有计算机程序，计算机程序被处理器执行时，处理器，可以用于执行如下步骤：The present invention also provides a computer-readable storage medium, which is used to implement the functions of the audio-based game beat calculation device, and stores a computer program thereon. When the computer program is executed by the processor, the processor , which can be used to perform the following steps:

获取待检测音频；Get the audio to be detected;

在本发明的一些实施例中，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, when the computer program stored in the computer-readable storage medium is executed by the processor, the processor can also be configured to implement the following steps:

在本发明的一些实施例中，所述节拍信息包括所述拍型信息和单位时间内的节拍数，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以具体用于实现如下步骤：In some embodiments of the present invention, the beat information includes the beat pattern information and the number of beats per unit time. When the computer program stored in the computer-readable storage medium is executed by the processor, the processor can also be specifically used for Implement the following steps:

在本发明的一些实施例中，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以具体用于实现如下步骤：In some embodiments of the present invention, when the computer program stored in the computer-readable storage medium is executed by the processor, the processor may also be specifically configured to implement the following steps:

在本发明的一些实施例中，在将所述多个声音能量突变点中的至少两个声音能量突变点合并为一个声音能量突变点之后，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, after combining at least two of the plurality of sound energy mutation points into one sound energy mutation point, the computer program stored in the computer-readable storage medium is executed by the processor , the processor can also be used to implement the following steps:

在本发明的一些实施例中，在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, the modified sound energy mutation point in the audio to be detected and at least one of the beat information, the rebeat information and the long beat information are mapped to the sound energy in the music game. Before the interaction point, when the computer program stored in the computer-readable storage medium is executed by the processor, the processor can also be used to implement the following steps:

在本发明的一些实施例中，在识别出所述待检测音频中的初始声音能量突变点之前，计算机可读存储介质存储的计算机程序被处理器执行时，处理器，还可以用于实现如下步骤：In some embodiments of the present invention, before the initial sound energy mutation point in the audio to be detected is identified, when the computer program stored in the computer-readable storage medium is executed by the processor, the processor may also be configured to implement the following: step:

可以理解的是，所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在相应的一个计算机可读取存储介质中。基于这样的理解，本发明实现上述相应的实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。It can be understood that, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a corresponding computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the process in the above-mentioned corresponding embodiment method, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Electric carrier signals and telecommunication signals are not included.

所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

Translated fromChinese

1.一种基于音频的游戏拍点映射方法，其特征在于，所述方法包括：1. a game beat mapping method based on audio, is characterized in that, described method comprises:

获取待检测音频；Get the audio to be detected;

2.根据权利要求1所述的方法，其特征在于，所述获取所述待检测音频的节拍信息，包括：2. The method according to claim 1, wherein the acquiring the beat information of the audio to be detected comprises:

3.根据权利要求2所述的方法，其特征在于，所述节拍信息包括所述拍型信息和单位时间内的节拍数；3. The method according to claim 2, wherein the beat information comprises the beat pattern information and the beat number per unit time;

4.根据权利3所述的方法，其特征在于，所述若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行删减操作，包括：4 . The method according to claim 3 , wherein, if multiple initial sound energy mutation points occur within a time not greater than half of the minimum time interval, the multiple initial sound energy mutation points Perform pruning operations, including:

5.根据权利要求4所述的方法，其特征在于，在将所述多个初始声音能量突变点中的至少两个初始声音能量突变点合并为一个初始声音能量突变点之后，所述方法还包括：5. The method according to claim 4, wherein after combining at least two initial sound energy mutation points in the plurality of initial sound energy mutation points into one initial sound energy mutation point, the method further comprises: include:

6.根据权利要求5所述的方法，其特征在于，所述若在不大于所述最小时间间隔一半的时间内，出现多个初始声音能量突变点，则对所述多个初始声音能量突变点执行调整操作，包括：6 . The method according to claim 5 , wherein if a plurality of initial sound energy mutation points occur within a time not greater than half of the minimum time interval, then the plurality of initial sound energy mutation Click to perform adjustment operations, including:

7.根据权利要求1所述的方法，其特征在于，所述方法还包括：7. The method of claim 1, wherein the method further comprises:

8.根据权利要求7所述的方法，其特征在于，所述识别出所述待检测音频中的长拍信息，包括：8. The method according to claim 7, wherein the identifying the long-beat information in the audio to be detected comprises:

9.根据权利要求7所述的方法，其特征在于，所述识别出所述待检测音频中的拍点信息和/或重拍信息，包括：9. The method according to claim 7, wherein the identifying the beat information and/or the rebeat information in the audio to be detected comprises:

10.根据权利要求7所述的方法，其特征在于，在将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点之前，所述方法还包括：10. The method according to claim 7, characterized in that, after correcting the sound energy mutation point in the audio to be detected, and at least one of the beat information, rebeat information and long beat information Before mapping to interactive points in the music game, the method further includes:

11.根据权利要求7所述的方法，其特征在于，所述将所述待检测音频中修正后的声音能量突变点，和所述拍点信息、重拍信息和长拍信息中的至少一项映射为音乐游戏中的互动点，包括：11. The method according to claim 7, wherein the modified sound energy mutation point in the audio to be detected, and at least one of the beat information, rebeat information and long beat information Items map to interactive points in the music game, including:

12.根据权利要求1至11所述的方法，其特征在于，在识别出所述待检测音频中的初始声音能量突变点之前，所述方法还包括：12. The method according to claims 1 to 11, wherein before identifying the initial sound energy mutation point in the audio to be detected, the method further comprises:

13.一种计算机装置，包括处理器和存储器，其特征在于，所述处理器在执行存储于存储器上的计算机程序时，用于实现如权利要求1至12中任一项所述的基于音频的游戏拍点映射方法。13. A computer device comprising a processor and a memory, characterized in that, when the processor executes a computer program stored in the memory, the processor is used to implement the audio-based audio-based audio system as claimed in any one of claims 1 to 12. The game tap mapping method.

14.一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时，用于实现如权利要求1至12中任一项所述的基于音频的游戏拍点映射方法。14. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, it is used to implement the audio-based audio-based recording method according to any one of claims 1 to 12. Game tap mapping method.