CN101039359B - Method, equipment and system for prompting addresser information in telephone conference - Google Patents
Method, equipment and system for prompting addresser information in telephone conferenceDownload PDFInfo
- Publication number
- CN101039359B CN101039359BCN200710098963XACN200710098963ACN101039359BCN 101039359 BCN101039359 BCN 101039359BCN 200710098963X ACN200710098963X ACN 200710098963XACN 200710098963 ACN200710098963 ACN 200710098963ACN 101039359 BCN101039359 BCN 101039359B
- Authority
- CN
- China
- Prior art keywords
- information
- speaker
- module
- media resource
- conference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及通信领域，特别涉及一种电话会议中提示发言人信息的方法、设备和系统。The invention relates to the communication field, in particular to a method, device and system for prompting speaker information in a teleconference.
背景技术Background technique
随着现代社会的发展，沟通交流越来越频繁，所涉及的范围也越来越广泛。各类商业、政治活动需要在更广泛的位置同时进行沟通、交流，如会议、协同工作等。这些分布式沟通是完成这些商业活动的的重要途径，而电话会议是分布式沟通的主要手段。它通过将各地与会人员接入会议中心，完成商业合作任务，从而大大提高了工作效率。With the development of modern society, communication is more and more frequent, and the scope involved is more and more extensive. All kinds of commercial and political activities need to communicate and exchange at the same time in a wider location, such as meetings and collaborative work. These distributed communications are an important way to complete these business activities, and teleconferencing is the main means of distributed communications. It connects participants from all over the conference center to complete business cooperation tasks, thereby greatly improving work efficiency.
电话会议系统随着技术的不断发展，从传统的基于PSTN(Public Switched TelephoneNetwork，公用电话交换网)的电话会议系统发展到基于IP(Internet Protocol，互联网协议)的多媒体电话会议系统，取得了很大的进步，电话会议系统也因此更加普及，人们使用也越来越多。With the continuous development of technology, the teleconferencing system has developed from the traditional PSTN-based (Public Switched Telephone Network) teleconferencing system to the IP (Internet Protocol, Internet Protocol)-based multimedia teleconferencing system. With the advancement of technology, teleconferencing systems have become more popular, and more and more people use them.
现有技术中有些电话会议系统有共享桌面，在共享桌面上有发言人个人信息的文本提示，对于使用共享桌面的与会人员，可以看到发言人个人信息的文本提示；有些电话会议系统当与会人员加入或退出时有语音提示，如语音提示“张先生加入了会议，李先生退出了会议”等等，但在会议过程中却没有发言人个人信息的提示。Some teleconferencing systems in the prior art have shared desktops, on which there are text prompts of the speaker’s personal information, and participants who use the shared desktop can see the text prompts of the speaker’s personal information; When a person joins or exits, there is a voice prompt, such as the voice prompt "Mr. Zhang has joined the meeting, and Mr. Li has withdrawn from the meeting", etc., but there is no prompt for the speaker's personal information during the meeting.
上述现有技术的缺点是对于普通电话接入的与会人员而言，不能得到发言人的个人信息，尤其是当与会人员比较多时，且在与会人员互相不熟悉的情况下，会议的沟通效果会随着与会人员的数目的增加而不断下降。即使是有视频的情况下，如果事先与会人员的个人信息没有互相介绍清楚，也会造成当发言人在会议过程中发言时，其他与会人员对该人的理解出现误差。例如，当张先生发言时，李先生还以为是赵先生在发言，导致会议结束后，李先生会向赵先生索要更详细的相关会议资料，或将张先生的反对意见理解为赵先生的反对意见，这种情况下发言人的个人信息不能很好地传达到每个与会人员，影响了电话会议的沟通效果。The disadvantage of the above-mentioned prior art is that for the participants connected by ordinary telephones, the personal information of the speaker cannot be obtained, especially when there are many participants and the participants are not familiar with each other, the communication effect of the meeting will be reduced. Decreases as the number of participants increases. Even in the case of video, if the personal information of the participants is not clearly introduced to each other in advance, it will cause errors in the understanding of the person by other participants when the speaker speaks during the meeting. For example, when Mr. Zhang made a speech, Mr. Li thought it was Mr. Zhao who was speaking. As a result, after the meeting, Mr. Li would ask Mr. Zhao for more detailed meeting materials, or interpret Mr. Zhang’s objection as Mr. Zhao’s objection In this case, the personal information of the speaker cannot be well conveyed to each participant, which affects the communication effect of the conference call.
发明内容Contents of the invention
为了使电话会议系统能够很好地提示发言人的信息，进而提高电话会议的沟通效果，本发明实施例提供了一种电话会议中提示发言人信息的方法、设备和系统。In order to enable the teleconference system to properly prompt the speaker's information and further improve the communication effect of the teleconference, the embodiments of the present invention provide a method, device and system for prompting the speaker's information in the teleconference.
本发明实施例提供的电话会议中提示发言人信息的方法包括：The method for prompting speaker information in a teleconference provided by an embodiment of the present invention includes:
会议媒体资源服务器接收并存储呼叫控制服务器发送的参会用户以语音形式提供的信息，所述信息包括所述参会用户的身份信息；The conference media resource server receives and stores the information provided by the participating users sent by the call control server in voice form, and the information includes the identity information of the participating users;
所述会议媒体资源服务器对发言人进行语音识别，并从存储的所述信息中提取出所述发言人的信息；The conference media resource server performs speech recognition on the speaker, and extracts the information of the speaker from the stored information;
所述会议媒体资源服务器将提取出的所述发言人的信息与所述发言人的发言内容语音合成后，通过所述呼叫控制服务器发送给所述参会用户，或者将提取出的所述发言人的信息转换成文本信息，通过所述呼叫控制服务器提供给所述参会用户；The conference media resource server synthesizes the extracted information of the speaker and the speech content of the speaker, and sends it to the participating users through the call control server, or sends the extracted speech The person's information is converted into text information, and provided to the participating users through the call control server;
其中，所述会议媒体资源服务器对发言人进行语音识别，包括：Wherein, the conference media resource server performs voice recognition on the speaker, including:
当有多个发言人同时发言时，所述会议媒体资源服务器按照预设的规则从所述多个发言人中选出一个发言人，进行语音识别，所述预设的规则为先选出各个会议地点音量最高的发言人，然后再从所有地点的音量最高的发言人中选择音量最高的发言人。When there are multiple speakers speaking at the same time, the conference media resource server selects a speaker from the multiple speakers according to preset rules for voice recognition. The loudest speaker at the meeting location, and then selects the loudest speaker from among the loudest speakers at all locations.
本发明实施例提供了一种会议媒体资源服务器，具体包括：接收模块、存储模块、识别模块和提示模块；An embodiment of the present invention provides a conference media resource server, specifically including: a receiving module, a storage module, an identification module and a prompt module;
所述接收模块，用于接收电话会议的呼叫控制服务器发来的参会用户在拨入电话会议时以语音的形式提供的信息，所述信息包括所述参会用户的身份信息；The receiving module is configured to receive the information provided by the conference call control server sent by the conference call server in the form of voice when the participating users dial into the conference call, the information includes the identity information of the participating users;
所述存储模块，用于存储所述接收模块收到的参会用户的信息；The storage module is used to store the information of the participating users received by the receiving module;
所述识别模块，用于对电话会议中的发言人进行语音识别，并从所述存储模块存储的参会用户的信息中提取出所述发言人的信息；The identification module is used to perform speech recognition on the speaker in the teleconference, and extract the information of the speaker from the information of the participating users stored in the storage module;
所述识别模块具体包括：The identification module specifically includes:
识别单元，用于当电话会议中有多个发言人同时发言时，按照预设的规则从所述多个发言人中选出一个发言人，进行语音识别，所述预设的规则为先选出各个会议地点音量最高的发言人，然后再从所有地点的音量最高的发言人中选择音量最高的发言人；The recognition unit is used to select a speaker from the plurality of speakers according to preset rules for speech recognition when there are multiple speakers speaking at the same time in the conference call, and the preset rule is to select first Find the speaker with the loudest volume in each meeting location, and then select the speaker with the loudest volume from the speakers with the loudest volume in all locations;
提取单元，用于当所述识别单元识别出所述发言人的身份后，从所述存储模块存储的参会用户的信息中提取出所述发言人的信息；An extracting unit, configured to extract the information of the speaker from the information of the participating users stored in the storage module after the identification unit recognizes the identity of the speaker;
所述提示模块，用于将所述识别模块提取出的所述发言人的信息与所述发言人的发言内容语音合成后，通过所述呼叫控制服务器发送给所述参会用户，或者将所述存储模块存储的文本格式的信息，通过所述呼叫控制服务器提供给所述参会用户；。The prompting module is configured to synthesize the information of the speaker extracted by the identification module and the speech content of the speaker, and then send it to the participating users through the call control server, or send the speech content of the speaker The information in text format stored by the storage module is provided to the participating users through the call control server;
其中，当所述提示模块将所述存储模块存储的文本格式的信息通过所述呼叫控制服务器提供给所述参会用户时，所述会议媒体资源服务器还包括：Wherein, when the prompt module provides the information in text format stored in the storage module to the participating users through the call control server, the conference media resource server further includes:
转换模块，用于将所述接收模块接收的参会用户的语音信息转换成所述文本格式的信息，并将所述文本格式的信息存储在所述存储模块中。The conversion module is used to convert the speech information of the participating users received by the receiving module into the information in the text format, and store the information in the text format in the storage module.
本发明实施例提供的电话会议中提示发言人信息的系统包括：会议媒体资源服务器和呼叫控制服务器，所述会议媒体资源服务器包括：接收模块、存储模块、识别模块和提示模块；The system for prompting speaker information in a teleconference provided by an embodiment of the present invention includes: a conference media resource server and a call control server, and the conference media resource server includes: a receiving module, a storage module, an identification module, and a prompt module;
所述接收模块，用于接收所述呼叫控制服务器发来的参会用户的信息；The receiving module is configured to receive the information of the participating users sent by the call control server;
所述存储模块，用于存储所述接收模块收到的参会用户的信息；The storage module is used to store the information of the participating users received by the receiving module;
所述识别模块，用于对电话会议中的发言人进行语音识别，并从所述存储模块存储的参会用户的信息中提取出所述发言人的信息；The identification module is used to perform speech recognition on the speaker in the teleconference, and extract the information of the speaker from the information of the participating users stored in the storage module;
所述识别模块具体包括：The identification module specifically includes:
识别单元，用于当电话会议中有多个发言人同时发言时，按照预设的规则从所述多个发言人中选出一个发言人，进行语音识别，所述预设的规则为先选出各个会议地点音量最高的发言人，然后再从所有地点的音量最高的发言人中选择音量最高的发言人；The recognition unit is used to select a speaker from the plurality of speakers according to preset rules for speech recognition when there are multiple speakers speaking at the same time in the conference call, and the preset rule is to select first Find the speaker with the loudest volume in each meeting location, and then select the speaker with the loudest volume from the speakers with the loudest volume in all locations;
提取单元，用于当所述识别单元识别出所述发言人的身份后，从所述存储模块存储的参会用户的信息中提取出所述发言人的信息；An extracting unit, configured to extract the information of the speaker from the information of the participating users stored in the storage module after the identification unit recognizes the identity of the speaker;
所述提示模块，用于将所述识别模块提取出的所述发言人的信息与所述发言人的发言内容语音合成后，传输给所述呼叫控制服务器，或者将所述存储模块存储的文本格式的信息传输给所述呼叫控制服务器；The prompting module is used to synthesize the information of the speaker extracted by the identification module and the speech content of the speaker, and then transmit the information to the call control server, or store the text stored in the storage module format information is transmitted to the call control server;
其中，当所述提示模块将所述存储模块存储的文本格式的信息传输给所述呼叫控制服务器时，所述会议媒体资源服务器还包括：Wherein, when the prompt module transmits the information in text format stored in the storage module to the call control server, the conference media resource server further includes:
转换模块，用于将所述接收模块接收的参会用户的语音信息转换成所述文本格式的信息，并将所述文本格式的信息存储在所述存储模块中；A conversion module, configured to convert the voice information of the participating users received by the receiving module into information in the text format, and store the information in the text format in the storage module;
所述呼叫控制服务器包括：The call control server includes:
发送模块，用于当参会用户拨入电话会议时，将所述参会用户以语音形式提供的信息发送给所述会议媒体资源服务器的接收模块；A sending module, configured to send the information provided by the participating user in voice form to the receiving module of the conference media resource server when the participating user dials into the conference call;
接收及转发模块，用于接收所述会议媒体资源服务器的提示模块发来的发言人信息，并转发给所述参会用户。The receiving and forwarding module is configured to receive the speaker information sent by the prompt module of the conference media resource server, and forward it to the participating users.
本发明实施例通过电话会议的呼叫控制服务器事先向会议媒体资源服务器提供参会用户的个人语音信息作为身份识别基础，会议媒体资源服务器根据语音特征识别发言人的身份信息，并将发言人的信息通过呼叫控制服务器提示给参会用户，明显地提高了电话会议的沟通效果。In the embodiment of the present invention, the call control server of the teleconference provides the conference media resource server with the personal voice information of the participating users as the basis for identification. The call control server notifies the participating users, which obviously improves the communication effect of the teleconference.
附图说明Description of drawings
图1是本发明实施例1提供的电话会议中提示发言人信息的方法流程图；FIG. 1 is a flow chart of a method for prompting speaker information in a conference call according to Embodiment 1 of the present invention;
图2是本发明实施例2提供的会议媒体资源服务器的结构图；FIG. 2 is a structural diagram of a conference media resource server provided by Embodiment 2 of the present invention;
图3是本发明实施例3提供的呼叫控制服务器的结构图；FIG. 3 is a structural diagram of a call control server provided by Embodiment 3 of the present invention;
图4是本发明实施例4提供的电话会议中提示发言人信息的系统结构图；FIG. 4 is a system structural diagram for prompting speaker information in a teleconference provided by Embodiment 4 of the present invention;
图5是本发明实施例4提供的电话会议中提示发言人信息的系统应用示意图。FIG. 5 is a schematic diagram of a system application for prompting speaker information in a conference call according to Embodiment 4 of the present invention.
具体实施方式Detailed ways
下面结合附图和具体实施例对本发明作进一步说明，但本发明不局限于下面的实施例。The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the present invention is not limited to the following embodiments.
本发明实施例通过电话会议的呼叫控制服务器事先向会议媒体资源服务器提供参会用户的个人语音信息作为身份识别基础，当某一个参会用户发言时，会议媒体资源服务器根据语音特征识别出发言人的身份信息，并将发言人的个人信息通过一个或多个呼叫控制服务器提示给多个参会用户，从而提高了电话会议的沟通效果。In the embodiment of the present invention, the call control server of the teleconference provides the conference media resource server with the personal voice information of the participating users as the basis for identity recognition. When a certain participating user speaks, the conference media resource server recognizes the speaker according to the voice characteristics The identity information of the speaker, and the personal information of the speaker is prompted to multiple participating users through one or more call control servers, thereby improving the communication effect of the conference call.
实施例1Example 1
参见图1，本发明实施例提供了一种电话会议中提示发言人信息的方法，具体包括以下步骤：Referring to Fig. 1, an embodiment of the present invention provides a method for prompting speaker information in a teleconference, which specifically includes the following steps:
步骤101：在会议媒体资源服务器上创建电话会议，并开通发言人提示业务。Step 101: Create a conference call on the conference media resource server, and activate the speaker notification service.
步骤102：电话会议的参会用户拨入电话会议；Step 102: the participating users of the conference call dial into the conference call;
参会用户可以通过电话和呼叫控制服务器拨入电话会议；参会用户也可以采用其他方式拨入电话会议，如用计算机拨入。Participants can dial into the conference call through the telephone and the call control server; participants can also use other methods to dial into the conference call, such as using a computer to dial in.
步骤103：会议媒体资源服务器收到呼叫控制服务器发来的参会用户加入电话会议的请求后，提示参会用户输入会议密码。Step 103: After receiving the request from the call control server from the call control server, the conference media resource server prompts the conference user to input the conference password.
步骤104：参会用户输入会议密码，验证通过后，以语音的形式向会议媒体资源服务器提供自己的信息，该信息中可以包括参会用户的身份信息；例如，姓名、职务和参加会议的地点等等。Step 104: The participating user enters the meeting password, and after passing the verification, provides their own information to the conference media resource server in the form of voice, and the information may include the identity information of the participating user; for example, name, title, and meeting location etc.
步骤105：会议媒体资源服务器存储参会用户以语音形式提供的个人信息；Step 105: the meeting media resource server stores the personal information provided by the participating users in voice form;
例如，会议媒体资源服务器对参会用户的语音信息进行采样，然后将采样得到的信号保存在一个数据库中，并建立采样信号与参会用户的对应关系。For example, the conference media resource server samples the speech information of the participating users, and then stores the sampled signals in a database, and establishes a corresponding relationship between the sampled signals and the participating users.
步骤106：发言人发言。Step 106: The speaker makes a speech.
步骤107：会议媒体资源服务器对发言人进行语音识别；Step 107: the conference media resource server performs speech recognition on the speaker;
例如，会议媒体资源服务器对发言人的声音进行采样，然后将得到的采样信号与数据库库中的采样信号进行匹配，匹配成功后，就可得到发言人的信息，即识别出发言人的身份；For example, the conference media resource server samples the voice of the speaker, and then matches the sampled signal with the sampled signal in the database. After the matching is successful, the information of the speaker can be obtained, that is, the identity of the speaker can be identified;
当有多个发言人同时发言时，会议媒体资源服务器可以按照一定的规则从多个发言人中选出一个发言人，进行语音识别；When there are multiple speakers speaking at the same time, the conference media resource server can select a speaker from the multiple speakers according to certain rules for voice recognition;
预设的规则有多种，例如，选出音量最高的发言人进行语音识别；另外，还可以结合地点和音量进行识别，例如，先选出各个会议地点音量最高的发言人，然后再从所有地点的音量最高的发言人中选出音量最高的发言人；如从深圳接入电话会议的发言人中选出王先生音量最高，从杭州接入电话会议的发言人中选出李先生音量最高，然后再从王先生和李先生中选出音量最高的发言人；这样有利于快速识别，效率高。There are many preset rules. For example, the speaker with the highest volume is selected for speech recognition; in addition, the location and volume can also be combined for recognition. For example, the speaker with the highest volume at each meeting location is selected first, and then from all Select the speaker with the highest volume from the speakers with the highest volume in the location; for example, select Mr. Wang from the speakers who access the conference call in Shenzhen with the highest volume, and select Mr. Li from the speakers who access the conference call in Hangzhou with the highest volume , and then select the speaker with the highest volume from Mr. Wang and Mr. Li; this is conducive to rapid identification and high efficiency.
步骤108：会议媒体资源服务器识别出发言人的身份后，从存储的电话会议参会用户的信息中提取出发言人的信息；Step 108: After identifying the speaker's identity, the conference media resource server extracts the speaker's information from the stored information of the conference call participants;
例如，会议媒体资源服务器识别出发言人为王先生后，从数据库中提取出王先生的信息，如王先生的职务为教授，参加会议的地点为深圳等。For example, after the conference media resource server identifies the speaker as Mr. Wang, it extracts Mr. Wang's information from the database, such as Mr. Wang's position as a professor, and the location of the conference as Shenzhen.
步骤109：会议媒体资源服务器通过呼叫控制服务器将提取的发言人的信息提示给参会用户。Step 109: The conference media resource server prompts the extracted speaker information to the conference participants through the call control server.
会议媒体资源服务器在进行提示时，可以采用语音形式，如先将发言人的发言内容与提取出的发言人的语音信息作语音合成处理，然后将合成后的语音信号传输给呼叫控制服务器；另外，也可以采用文本形式，如将提取出的发言人的语音信息转换成文本信息，然后将该文本信息传输给呼叫控制服务器。When the conference media resource server prompts, it can use the voice form, such as first performing speech synthesis processing on the speaker's speech content and the extracted speaker's voice information, and then transmitting the synthesized voice signal to the call control server; in addition , can also be in the form of text, such as converting the extracted speech information of the speaker into text information, and then transmitting the text information to the call control server.
为了提高应用的灵活性，进一步地，上述方法还可以包括下面的步骤：In order to improve the flexibility of the application, further, the above method may also include the following steps:
会议媒体资源服务器在进行语音识别之前，先判断参会用户是否需要会议媒体资源服务器提示发言人的信息，如果是，则执行步骤107，即进行语音识别；否则，不进行提示，结束当前流程。Before performing speech recognition, the conference media resource server first judges whether the participating users need the conference media resource server to prompt the information of the speaker, if yes, execute step 107, that is, perform speech recognition; otherwise, do not prompt and end the current process.
另外，上述方法也可以包括下面的步骤：In addition, the above method may also include the following steps:
会议媒体资源服务器在进行提示之前，先判断参会用户是否需要会议媒体资源服务器提示发言人的信息，如果是，则执行步骤109，即直接进行提示；否则，不进行提示，结束当前流程。Before prompting, the conference media resource server first judges whether the participating users need the conference media resource server to prompt the information of the speaker, if yes, execute step 109, that is, prompt directly; otherwise, end the current process without prompting.
实施例2Example 2
参见图2，本发明实施例还提供了一种会议媒体资源服务器，具体包括：Referring to Fig. 2, the embodiment of the present invention also provides a kind of meeting media resource server, specifically comprises:
(1)接收模块，用于接收电话会议的呼叫控制服务器发来的参会用户在拨入电话会议时以语音的形式提供的信息，信息包括参会用户的身份信息；(1) The receiving module is used to receive the information provided by the participating users in the form of voice when the call control server of the conference call sends them, and the information includes the identity information of the participating users;
(2)存储模块，用于存储接收模块收到的参会用户的信息；(2) a storage module, used to store the information of the participating users received by the receiving module;
(3)识别模块，用于对电话会议中的发言人进行语音识别，识别出发言人的身份后，从存储模块存储的参会用户的信息中提取出发言人的信息；(3) The recognition module is used to carry out speech recognition to the speaker in the teleconference, and after identifying the identity of the speaker, extracts the information of the speaker from the information of the participating users stored in the storage module;
(4)提示模块，用于通过呼叫控制服务器将识别模块得到的发言人的信息提示给电话会议的参会用户。(4) A prompting module, configured to prompt the speaker's information obtained by the identification module to the participating users of the teleconference through the call control server.
当有多个发言人同时发言时，进一步地，上述识别模块可以具体包括：When there are multiple speakers speaking at the same time, further, the above identification module may specifically include:
识别单元，用于当电话会议中有多个发言人同时发言时，按照预设的规则从多个发言人中选出一个发言人，进行语音识别；例如，选出音量最高的发言人；The recognition unit is used to select a speaker from the multiple speakers according to preset rules when there are multiple speakers speaking at the same time in the conference call, for voice recognition; for example, to select the speaker with the highest volume;
提取单元，用于当识别单元识别出发言人的身份后，从存储模块存储的参会用户的信息中提取出发言人的信息。The extracting unit is used to extract the information of the speaker from the information of the participating users stored in the storage module after the identification unit recognizes the identity of the speaker.
为了提高应用的灵活性，进一步地，上述会议媒体资源服务器还可以包括：In order to improve the flexibility of the application, further, the above conference media resource server may also include:
判断模块，用于判断参会用户是否需要会议媒体资源服务器提示发言人的信息，如果是，则触发上述识别模块工作。The judging module is used to judge whether the participating users need the conference media resource server to prompt the speaker's information, and if so, trigger the above identification module to work.
在实际应用中，判断模块也可以在参会用户需要提示时，直接触发上述提示模块工作。In practical applications, the judging module can also directly trigger the prompting module to work when the participating users need to be prompted.
进一步地，上述会议媒体资源服务器还可以包括：Further, the above conference media resource server may also include:
转换模块，用于将接收模块接收的参会用户的语音信息转换成文本格式的信息，并将该文本格式的信息存储在上述存储模块中。The conversion module is used to convert the voice information of the participating users received by the receiving module into information in text format, and store the information in text format in the above-mentioned storage module.
上述提示模块给参会用户提示发言人的信息时，可以采用文本形式，如将转换模块转换后并存储在存储模块中的文本信息，通过呼叫控制服务器发送给参会用户；也可以采用语音形式，如将识别模块提取出的发言人的语音信息与发言人的发言内容语音合成后，通过呼叫控制服务器发送给参会用户。When the above-mentioned prompting module reminds the participating users of the information of the speaker, it can be in the form of text, such as the text information converted by the conversion module and stored in the storage module, and sent to the participating users through the call control server; it can also be in the form of voice For example, the voice information of the speaker extracted by the recognition module is synthesized with the content of the speaker's speech, and then sent to the participating users through the call control server.
实施例3Example 3
参见图3，本发明实施例还提供了一种呼叫控制服务器，具体包括：Referring to Fig. 3, the embodiment of the present invention also provides a call control server, which specifically includes:
(1)发送模块，用于当参会用户拨入电话会议时，将参会用户以语音的形式提供的信息发送给电话会议的会议媒体资源服务器；(1) a sending module, used for sending the information provided by the participating user in the form of voice to the conference media resource server of the teleconference when the participating user dials into the conference call;
(2)接收及转发模块，用于接收会议媒体资源服务器发来的发言人信息的提示，并转发给参会用户。(2) The receiving and forwarding module is used to receive the reminder of speaker information sent by the conference media resource server and forward it to the participating users.
上述发送模块进行发送与上述接收及转发模块进行接收及转发，是通过呼叫控制信令和媒体或单独通过呼叫控制信令来完成的。The sending by the sending module and the receiving and forwarding by the receiving and forwarding module are completed through call control signaling and media or through call control signaling alone.
为了提高应用的灵活性，进一步地，上述发送模块还用于向会议媒体资源服务器发送参会用户需要提示发言人信息的请求。In order to improve the flexibility of the application, further, the above-mentioned sending module is further configured to send a request that the participating users need to be prompted for speaker information to the conference media resource server.
实施例4Example 4
参见图4，本发明实施例还提供了一种电话会议中提示发言人信息的系统，具体包括：会议媒体资源服务器和呼叫控制服务器，会议媒体资源服务器包括：Referring to FIG. 4 , an embodiment of the present invention also provides a system for prompting speaker information in a teleconference, specifically including: a conference media resource server and a call control server, and the conference media resource server includes:
(1)接收模块，用于接收呼叫控制服务器发来的参会用户的信息；(1) a receiving module, used to receive the information of the participating users sent by the call control server;
(2)存储模块，用于存储接收模块收到的参会用户的信息；(2) a storage module, used to store the information of the participating users received by the receiving module;
(3)识别模块，用于对电话会议中的发言人进行语音识别，识别出发言人的身份后，从存储模块存储的参会用户的信息中提取出发言人的信息；(3) The recognition module is used to carry out speech recognition to the speaker in the teleconference, and after identifying the identity of the speaker, extracts the information of the speaker from the information of the participating users stored in the storage module;
(4)提示模块，用于将识别模块得到的发言人的信息传输给呼叫控制服务器；(4) a prompting module, used to transmit the information of the speaker obtained by the identification module to the call control server;
呼叫控制服务器包括：Call control servers include:
(1)发送模块，用于当参会用户拨入电话会议时，将参会用户以语音形式提供的信息发送给会议媒体资源服务器的接收模块；(1) a sending module, used to send the information provided by the participating users in voice form to the receiving module of the conference media resource server when the participating users dial into the conference call;
(2)接收及转发模块，用于接收会议媒体资源服务器的提示模块发来的发言人信息，并转发给参会用户。(2) The receiving and forwarding module is used to receive the speaker information sent by the prompt module of the conference media resource server and forward it to the participating users.
上述会议媒体资源服务器还可以进一步包括：The above conference media resource server may further include:
转换模块，用于将接收模块接收的参会用户的语音信息转换成文本格式的信息，并将该文本格式的信息存储在上述存储模块中。The conversion module is used to convert the voice information of the participating users received by the receiving module into information in text format, and store the information in text format in the above-mentioned storage module.
提示模块给参会用户提示发言人的信息时，可以采用文本形式，如将转换模块转换后并存储在存储模块中的文本格式的信息传输给呼叫控制服务器；也可以采用语音形式，如将识别模块提取出的发言人的语音信息与发言人的发言内容语音合成后传输给呼叫控制服务器。When the prompting module prompts the information of the speaker to the participating users, it can be in the form of text, such as transmitting the information in the text format converted by the conversion module and stored in the storage module to the call control server; it can also be in the form of voice, such as identifying The speaker's voice information extracted by the module is synthesized with the speaker's speech content, and then transmitted to the call control server.
当有多个发言人同时发言时，进一步地，上述识别模块可以具体包括：When there are multiple speakers speaking at the same time, further, the above identification module may specifically include:
识别单元，用于当电话会议中有多个发言人同时发言时，按照预设的规则从多个发言人中选出音量最高的发言人，进行语音识别；The recognition unit is used to select the speaker with the highest volume from the speakers according to preset rules when there are multiple speakers speaking at the same time in the conference call for voice recognition;
提取单元，用于当识别单元识别出发言人的身份后，从存储模块存储的参会用户的信息中提取出发言人的信息。The extracting unit is used to extract the information of the speaker from the information of the participating users stored in the storage module after the identification unit recognizes the identity of the speaker.
为了提高应用的灵活性，进一步地，上述发送模块还用于向会议媒体资源服务器发送参会用户需要提示发言人信息的请求；In order to improve the flexibility of the application, further, the above-mentioned sending module is also used to send a request that the participating users need to be prompted for the information of the speaker to the conference media resource server;
相应地，会议媒体资源服务器的接收模块还用于接收发送模块发来的请求；Correspondingly, the receiving module of the meeting media resource server is also used to receive the request sent by the sending module;
而且上述会议媒体资源服务器还可以包括：Moreover, the above conference media resource server may also include:
判断模块，用于当会议媒体资源服务器的接收模块收到的参会用户发来的请求后，触发上述识别模块工作。The judging module is used to trigger the identification module to work when the receiving module of the conference media resource server receives the request from the participating users.
在实际应用中，判断模块也可以在参会用户需要提示时，直接触发上述提示模块工作。In practical applications, the judging module can also directly trigger the prompting module to work when the participating users need to be prompted.
上述电话会议中提示发言人信息的系统应用的场景很多，例如，参见图5，会议媒体资源服务器在深圳开通电话会议，北京有两个用户，用户A和用户B，通过电话和呼叫控制服务器1拨入电话会议；上海有一个用户，用户C，通过计算机和呼叫控制服务器2拨入电话会议；南京有两个用户，用户D和用户E，通过电话和呼叫控制服务器3拨入电话会议；当用户A、用户C和用户D同时发言时，会议媒体资源服务器选出音量最高的发言人，如用户A，进行语音识别，然后将用户A的个人语音信息以语音形式或文本形式通过呼叫控制服务器1、呼叫控制服务器2和呼叫控制服务器3提示给所有用户；或者提示给需要提示的用户。There are many application scenarios for the system that prompts the speaker’s information in the above conference call. For example, see Figure 5. The conference media resource server opens a conference call in Shenzhen. There are two users in Beijing, user A and user B, who control server 1 through the phone and call. Dial into the conference call; there is a user in Shanghai, user C, who dials into the conference call through the computer and the call control server 2; there are two users in Nanjing, user D and user E, who dial in the conference call through the phone and the call control server 3; When user A, user C, and user D speak at the same time, the conference media resource server selects the loudest speaker, such as user A, for voice recognition, and then sends user A's personal voice information in the form of voice or text to the call control server 1. The call control server 2 and the call control server 3 notify all users; or notify users who need to be notified.
本发明实施例可以利用软件实现，相应的软件可以存储在可读取的存储介质中，如计算机或服务器的硬盘和内存中。The embodiment of the present invention can be implemented by software, and the corresponding software can be stored in a readable storage medium, such as a hard disk and memory of a computer or server.
本发明实施例在电话会议过程中通过语音形式或文本形式提示发言人的信息，使与会人员之间的信息理解更加快速和准确，明显地提高了电话会议的沟通效果；且不限制与会人员拨入电话会议的形式；通过判断参会用户是否需要提示，给需要提示的参会用户提示发言人的信息，给不需要提示的参会用户播放发言内容，使应用更加灵活、方便。The embodiment of the present invention prompts the speaker's information in the form of voice or text during the teleconference, so that the information understanding between the participants is faster and more accurate, and the communication effect of the teleconference is obviously improved; and does not limit the participants to dial The form of entering a conference call; by judging whether the participating users need to be reminded, the speaker's information is prompted to the participating users who need to be reminded, and the speech content is played to the participating users who do not need to be reminded, making the application more flexible and convenient.
以上所述的实施例，只是本发明较优选的具体实施方式，本领域的技术人员在本发明技术方案范围内进行的通常变化和替换都应包含在本发明的保护范围内。The above-described embodiments are only preferred specific implementations of the present invention, and ordinary changes and replacements performed by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.
Claims (6)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710098963XACN101039359B (en) | 2007-04-30 | 2007-04-30 | Method, equipment and system for prompting addresser information in telephone conference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710098963XACN101039359B (en) | 2007-04-30 | 2007-04-30 | Method, equipment and system for prompting addresser information in telephone conference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101039359A CN101039359A (en) | 2007-09-19 |
| CN101039359Btrue CN101039359B (en) | 2011-11-16 |
Family
ID=38889981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200710098963XAActiveCN101039359B (en) | 2007-04-30 | 2007-04-30 | Method, equipment and system for prompting addresser information in telephone conference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101039359B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8050917B2 (en)* | 2007-09-27 | 2011-11-01 | Siemens Enterprise Communications, Inc. | Method and apparatus for identification of conference call participants |
| WO2011090411A1 (en)* | 2010-01-20 | 2011-07-28 | Telefonaktiebolaget Lm Ericsson (Publ) | Meeting room participant recogniser |
| US8892123B2 (en)* | 2012-03-07 | 2014-11-18 | Microsoft Corporation | Identifying meeting attendees using information from devices |
| WO2014068788A1 (en)* | 2012-11-05 | 2014-05-08 | 三菱電機株式会社 | Speech recognition device |
| TW201513673A (en) | 2013-09-30 | 2015-04-01 | Ibm | Method and computer program product for automatically joining a peer-to-peer communication dialogue |
| CN104639777A (en)* | 2013-11-14 | 2015-05-20 | 中兴通讯股份有限公司 | Conference control method, conference control device and conference system |
| CN105407125B (en)* | 2014-09-16 | 2018-08-28 | 国际商业机器公司 | It is automatically added to the method and system of point-to-point communication session |
| CN104767963B (en)* | 2015-03-27 | 2018-10-09 | 华为技术有限公司 | Participant's information demonstrating method in video conference and device |
| CN106057193A (en)* | 2016-07-13 | 2016-10-26 | 深圳市沃特沃德股份有限公司 | Conference record generation method based on telephone conference and device |
| CN108206817B (en)* | 2016-12-20 | 2020-12-22 | 中移（杭州）信息技术有限公司 | Method and device for selecting a conference route |
| CN112420047A (en)* | 2019-08-23 | 2021-02-26 | 珠海金山办公软件有限公司 | Communication method, device, user terminal and storage medium for network conference |
| CN115134476B (en)* | 2021-03-29 | 2025-09-09 | 明基智能科技（上海）有限公司 | Image sharing and conference participant identification method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584982A (en)* | 2003-08-04 | 2005-02-23 | 索尼株式会社 | Speech processing device |
- 2007
- 2007-04-30CNCN200710098963XApatent/CN101039359B/enactiveActive
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584982A (en)* | 2003-08-04 | 2005-02-23 | 索尼株式会社 | Speech processing device |
Non-Patent Citations (1)
| Title |
|---|
| JP特开平7-107451A 1995.04.21 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101039359A (en) | 2007-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101039359B (en) | Method, equipment and system for prompting addresser information in telephone conference | |
| US10623563B2 (en) | System and methods for providing voice transcription | |
| CN100546322C (en) | Chat and tele-conferencing system with the translation of Text To Speech and speech-to-text | |
| CN100486284C (en) | System and method of managing personal telephone recording | |
| US20050206721A1 (en) | Method and apparatus for disseminating information associated with an active conference participant to other conference participants | |
| US8270606B2 (en) | Open architecture based domain dependent real time multi-lingual communication service | |
| CN103475499B (en) | A kind of speech talkback method and system based on network telephone conference | |
| US20090296908A1 (en) | Telecommunications Endpoint that Prompts a User to Focus on a Monitored Call | |
| US20120259924A1 (en) | Method and apparatus for providing summary information in a live media session | |
| US20090135741A1 (en) | Regulated voice conferencing with optional distributed speech-to-text recognition | |
| CN106301811A (en) | Realize the method and device of multimedia conferencing | |
| US20140269678A1 (en) | Method for providing an application service, including a managed translation service | |
| CN104137523B (en) | A kind of method, apparatus and system that realize meeting access | |
| CN101754143B (en) | Mobile terminal and method thereof for improving supplementary service of multi-party call | |
| CN103067188A (en) | Network phone conference system and implementation method thereof | |
| JP2012257116A (en) | Text and telephone conference system and text and telephone conference method | |
| CN104579710B (en) | The asynchronous conference system of fragmentation | |
| JP2015041885A (en) | Video conference system | |
| CN104579715A (en) | High-communication-quality teleconference system and method | |
| CN104469254B (en) | Meeting roll-call processing method, device and conference system | |
| JP4787328B2 (en) | Method and apparatus for capturing audio during a conference call | |
| CN111028837B (en) | Voice conversation method, voice recognition system and computer storage medium | |
| US8842813B2 (en) | Teleconferencing monitoring method | |
| JP2007201906A (en) | Portable terminal device and image display method | |
| CN102196106B (en) | Method and related equipment for realizing call between calling party and called party |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |