TWI743624B - Attention assist system - Google Patents

Abstract

Translated fromChinese

一種注意力集中輔助系統，包含用以設置在講者與聽者間的收音裝置，及用以供聽者配戴的耳機裝置。該收音裝置可分析收音得到之聲音訊號中的語音成分以得到一語音音源方向，並以波束成形技術朝該語音音源方向進行語音提取以得到一語音訊號，且將該語音訊號傳送至該耳機裝置輸出。透過在該講者與該聽者間設置該收音裝置，以追蹤該講者的語音方向並進行語音提取，並經由該耳機裝置輸出所提取的語音訊號供聽者聆聽的設計，可在阻隔周遭環境聲音干擾的情況下，協助具有注意力不集中症狀的該聽者將注意力集中向該講者。An attention concentration assisting system includes a radio device set between the speaker and the listener, and an earphone device for the listener to wear. The radio device can analyze the voice component in the sound signal obtained by the radio to obtain a voice source direction, and use beamforming technology to perform voice extraction toward the voice source direction to obtain a voice signal, and transmit the voice signal to the earphone device Output. By setting up the radio device between the speaker and the listener to track the speaker’s voice direction and perform voice extraction, and output the extracted voice signal through the earphone device for the listener to listen to, the design can block the surrounding In the case of environmental sound interference, assist the listener with inattention symptoms to focus on the speaker.

Description

Translated fromChinese

注意力集中輔助系統Attention assist system

本發明是有關於一種輔具，特別是指一種用以輔助集中注意力的輔助系統。The present invention relates to an auxiliary device, in particular to an auxiliary system for assisting concentration.

注意力不集中是一種會影響學習與生活的症狀，有注意力不集中症狀的學童的注意力容易因周遭一點聲音刺激而被轉移，無法專心聽講與做功課，也很難集中注意力完成一件工作或遊戲。如不適時進行治療，會嚴重影響學童的學習與成長。Inattention is a symptom that affects study and life. School children with inattention symptoms are easily diverted due to a little sound stimulation around them, unable to concentrate on listening and doing homework, and it is difficult to concentrate on completing one. Piece of work or game. If treatment is not performed in time, it will seriously affect the learning and growth of school children.

目前針對注意力不集中症狀的主要治療方式為藥物治療，特別是當學童本身症狀已嚴重妨礙到學習、人際關係及人格發展時，藥物治療可以有效幫助這些學童。但因為治療藥物會引發一些副作用，例如頭痛、腸胃不適、食慾降低、噁心及失眠等，所以許多家長與老師擔心藥物治療會影響學童的成長發育與生活作息，而排斥採用藥物治療。At present, the main treatment method for the symptoms of inattention is medication, especially when the school children's own symptoms have seriously hindered learning, interpersonal relationship and personality development, medication can effectively help these school children. However, because treatment drugs can cause some side effects, such as headache, gastrointestinal discomfort, decreased appetite, nausea, and insomnia, many parents and teachers worry that drug treatment will affect the growth and development of school children and their daily routines and reject the use of drug treatment.

因此，本發明的目的，即在提供一種可用以輔助改善注意力不集中症狀的注意力集中輔助系統。Therefore, the purpose of the present invention is to provide an attention assistance system that can be used to assist in improving the symptoms of inattention.

於是，本發明注意力集中輔助系統，包含一個用以設置在一位講者與一位聽者間的收音裝置，及一個用以供該聽者配戴的耳機裝置。該收音裝置包括一個麥克風陣列、一個第一通訊模組、一個語音追蹤模組，及一個語音提取模組，該麥克風陣列具有多個用以朝該講者一側收音的麥克風，該語音追蹤模組可分析該等麥克風收音得到之聲音訊號中的語音成分，以定位得到語音訊號最強的一個語音音源方向，該語音提取模組會以波束成形技術控制該麥克風陣列朝該語音音源方向進行語音提取以得到一個語音訊號，並經由該第一通訊模組對該耳機裝置無線發送該語音訊號。該耳機裝置包括一個用以無線接收該語音訊號之第二通訊模組，及一個用以供配戴於該聽者之雙耳且用以輸出該語音訊號的耳機本體。Therefore, the attention assistance system of the present invention includes a radio device for setting between a speaker and a listener, and an earphone device for the listener to wear. The radio device includes a microphone array, a first communication module, a voice tracking module, and a voice extraction module. The microphone array has a plurality of microphones for receiving sound toward the speaker. The voice tracking module The group can analyze the voice components in the sound signals received by the microphones to locate the direction of the voice source with the strongest voice signal. The voice extraction module uses beamforming technology to control the microphone array toward the voice source direction for voice extraction To obtain a voice signal, and wirelessly send the voice signal to the earphone device through the first communication module. The earphone device includes a second communication module for wirelessly receiving the voice signal, and an earphone body for being worn on both ears of the listener and for outputting the voice signal.

於是，本發明注意力集中輔助系統，包含一個用以設置在一位講者與一位聽者間的收音裝置，及用以供該聽者攜帶的一個隨身裝置與一個耳機裝置。該收音裝置包括一個麥克風陣列、一個第一通訊模組、一個用以朝該講者一側進行影像擷取以得到一個講方影像的影像擷取模組，及一個語音提取模組，該麥克風陣列具有多個用以朝該講者一側收音的麥克風，該語音提取模組會以波束成形技術控制該麥克風陣列朝該講方影像中的一個講者方位進行語音提取以得到一個語音訊號，該第一通訊模組會透過無線通訊技術將該講方影像與該語音訊號發送給該隨身裝置。該隨身裝置包括一個用以無線接收該講方影像與該語音訊號的第三通訊模組，及一個講者追蹤模組，該講者追蹤模組可分析該講方影像中之人物以定位得到該講者方位，並經由該第三通訊模組對該第一通訊模組對應回傳該講者方位，並透過有線及/或無線通訊技術對該耳機裝置發送該語音訊號。該耳機裝置包括一個用以接收該第三通訊模組發送之該語音訊號的第二通訊模組，及一個用以供配戴於該聽者之雙耳且用以輸出該語音訊號的耳機本體。Therefore, the attention assistance system of the present invention includes a radio device for setting between a speaker and a listener, and a portable device and a headphone device for the listener to carry. The radio device includes a microphone array, a first communication module, an image capturing module for capturing images toward the speaker to obtain an image of the speaker, and a voice extracting module. The microphone The array has a plurality of microphones for receiving sound toward the speaker side, and the voice extraction module uses beamforming technology to control the microphone array to perform voice extraction toward a speaker position in the speaker image to obtain a voice signal, The first communication module sends the speaker image and the voice signal to the portable device through wireless communication technology. The portable device includes a third communication module for wirelessly receiving the speaker image and the voice signal, and a speaker tracking module, the speaker tracking module can analyze the person in the speaker image to locate The position of the speaker is returned to the first communication module through the third communication module, and the voice signal is sent to the earphone device through wired and/or wireless communication technology. The earphone device includes a second communication module for receiving the voice signal sent by the third communication module, and an earphone body for being worn on the listener's ears and for outputting the voice signal .

本發明的功效在於：透過在該講者與該聽者間設置該收音裝置，並以該收音裝置追蹤該講者的語音方向或講者方位以進行語音提取的設計，可在阻隔周遭環境聲音干擾的情況下，讓該聽者直接聆聽該講者的講話內容，而可用以協助具有注意力不集中症狀的該聽者將注意力集中向該講者。The effect of the present invention is that by setting the radio device between the speaker and the listener, and using the radio device to track the speaker's voice direction or speaker position for voice extraction, the design can block surrounding environmental sounds. In the case of interference, the listener is allowed to directly listen to the content of the speaker's speech, which can be used to assist the listener with inattention symptoms to focus on the speaker.

在本發明被詳細描述前，應當注意在以下的說明內容中，類似的元件是以相同的編號來表示。Before the present invention is described in detail, it should be noted that in the following description, similar elements are denoted by the same numbers.

參閱圖1、2、3，本發明注意力集中輔助系統200的第一實施例，包含一個用以設置在一位講者800與一位聽者900間的收音裝置3，及一個用以供該聽者900配戴的耳機裝置4。在本第一實施例中，是以將該收音裝置3設置在一個講堂的一個講台700上為例進行說明，使該收音裝置3間隔位於一個書寫板701（黑板或白板）前方，可用以對該站在該書寫板701與該講台700間的一位講者800進行收音，並將收音內容傳送至該聽者900配戴的該耳機裝置4。所述講者800例如但不限於老師，所述聽者900例如但不限於具有注意力不集中症狀的學童。Referring to Figures 1, 2, and 3, the first embodiment of theattention assistance system 200 of the present invention includes aradio device 3 for setting between aspeaker 800 and alistener 900, and a device for Theearphone device 4 worn by thelistener 900. In this first embodiment, theradio device 3 is set on apodium 700 in a lecture hall as an example for description. Theradio device 3 is spaced in front of a writing board 701 (blackboard or whiteboard), which can be used to Thespeaker 800 standing between thewriting board 701 and thepodium 700 picks up the sound, and transmits the radio content to theearphone device 4 worn by thelistener 900. Thespeaker 800 is, for example, but not limited to, a teacher, and thelistener 900 is, for example, but not limited to, school children with inattention symptoms.

該收音裝置3包括一個機殼30，以及安裝在該機殼30的一個麥克風陣列31、一個第一通訊模組32、一個影像擷取模組33、一個講者追蹤模組34、一個語音追蹤模組35與一個語音提取模組36。Theradio device 3 includes ahousing 30, amicrophone array 31, afirst communication module 32, animage capturing module 33, aspeaker tracking module 34, and a voice tracking module installed in thehousing 30.Module 35 and avoice extraction module 36.

該麥克風陣列31包括多個間隔設置在該機殼30且可用以朝該講者800一側收音的麥克風311。該第一通訊模組32可透過目前已知的無線通訊技術與該耳機裝置4進行通訊，所述無線通訊技術例如但不限於wifi與藍芽等。該影像擷取模組33可用以朝該機殼30面向該講者800一側進行影像擷取以得到一個講方影像。Themicrophone array 31 includes a plurality ofmicrophones 311 arranged at intervals on thecasing 30 and used for receiving sound toward thespeaker 800 side. Thefirst communication module 32 can communicate with theearphone device 4 through currently known wireless communication technologies, such as but not limited to wifi and Bluetooth. The image capturingmodule 33 can be used to capture images toward the side of thecabinet 30 facing thespeaker 800 to obtain a speaker image.

該講者追蹤模組34可供操作以啟動該影像擷取模組33進行影像擷取，可經由該影像擷取模組33擷取該講者800的人物影像，例如擷取該講者800的正面、左右兩側面及/或背後的人物影像。實施時，在本發明之其它實施態樣中，該講者追蹤模組34也可改為能供透過其它輸入介面來輸入該講者800的人物影像。此外，所述講者800的人物影像例如但不限於頭部，或者是半身照、全身照等。所述輸入介面例如但不限於USB介面。Thespeaker tracking module 34 can be operated to activate the image capturingmodule 33 for image capturing, and theimage capturing module 33 can capture the character image of thespeaker 800, such as capturing thespeaker 800 Images of people on the front, left and right sides, and/or behind. In implementation, in other implementation aspects of the present invention, thespeaker tracking module 34 can also be adapted to input the person image of thespeaker 800 through other input interfaces. In addition, the person image of thespeaker 800 is, for example, but not limited to, a head, a half-length photo, a full-length photo, or the like. The input interface is, for example, but not limited to, a USB interface.

該講者追蹤模組34包括一個講者特徵建立單元341、一個講者特徵比對單元342，及一個講者追蹤單元343。該講者特徵建立單元341會分析擷取該講者800的所有人物影像的人物特徵以建立一個講者影像特徵參數。在本實施例中，是擷取每一人物影像中的頭部影像區域的人物特徵來建立該講者影像特徵參數，所述人物特徵例如但不限於臉形、臉部五官外形等特徵，但實施時，在本發明之另一實施態樣中，還可進一步分析每一人物影像的衣著的顏色、花紋與型態等來得到所述人物特徵，並彙整前述頭部影像區域的人物特徵與衣著的人物特徵以建立該講者影像特徵參數。由於透過分析人物影像之人物特徵以建立該講者影像特徵參數的方式眾多，因此實施時不以上述態樣為限。Thespeaker tracking module 34 includes a speakerfeature establishing unit 341, a speaker feature comparing unit 342, and aspeaker tracking unit 343. The speakerfeature creation unit 341 analyzes and captures the character features of all the person images of thespeaker 800 to create a speaker image feature parameter. In this embodiment, the person characteristics of the head image area in each person image are captured to establish the speaker image feature parameters, such as but not limited to features such as face shape, facial features, etc., but the implementation At this time, in another embodiment of the present invention, the color, pattern, and shape of the clothing of each person image can be further analyzed to obtain the person characteristics, and the person characteristics and clothing in the aforementioned head image area can be aggregated. Character characteristics to establish the speaker’s image characteristic parameters. Since there are many ways to establish the feature parameters of the speaker's image by analyzing the character characteristics of the person image, the implementation is not limited to the above-mentioned aspect.

該講者特徵比對單元342可根據該講者影像特徵參數分析該講方影像中所存在之人物影像的影像特徵，判斷該講方影像中是否存在該講者800，藉以從該講方影像中識別出對應該講者800的一個講者影像。該講者追蹤單元343會分析定位出該講者影像於該講方影像中的位置以得到一個講者方位。The speaker feature comparison unit 342 can analyze the image features of the person images in the speaker image according to the speaker image feature parameters, and determine whether thespeaker 800 is present in the speaker image, so as to obtain information from the speaker image A speaker image corresponding to thespeaker 800 is identified in. Thespeaker tracking unit 343 analyzes and locates the position of the speaker image in the speaker image to obtain a speaker position.

該語音追蹤模組35可分析該等麥克風311收音得到之該等聲音訊號中的語音成分，以該從等聲音訊號中定位得到語音訊號最強的一個語音音源方向。由於該等麥克風311是嵌裝外露在該機殼30面向該講者800一側，所以主要收音方向是朝向該講者800一側，對於該機殼30背向該講者800一側的收音效果極差，所以從該等麥克風311的該等聲音訊號分析得到的語音訊號最強者就可判斷是來自該講者800。Thevoice tracking module 35 can analyze the voice components in the voice signals received by themicrophones 311, and locate the voice source direction with the strongest voice signal from the isophonic signals. Since themicrophones 311 are embedded and exposed on the side of thecasing 30 facing thespeaker 800, the main sound receiving direction is toward the side of thespeaker 800. For the side of thecasing 30 facing away from thespeaker 800, The effect is extremely poor. Therefore, the strongest voice signal obtained from the analysis of the sound signals of themicrophones 311 can be judged to come from thespeaker 800.

該語音提取模組36內建有一個語音追蹤模式361與一個影像追蹤模式362，於啟動該語音追蹤模式361時，該語音提取模組36會觸發啟動該麥克風陣列31進行收音，且觸發該語音追蹤模組35定位得到該語音音源方向，然後，該語音提取模組36會以波束成形技術控制該麥克風陣列31朝該語音音源方向進行語音提取以得到一個語音訊號；於啟動該影像追蹤模式362時，該語音提取模組36會觸發該影像擷取模組33擷取得到該講方影像，且會觸發該講者追蹤模組34分析該講方影像以定位得到該講者方位，然後，該語音提取模組36會以波束成形技術控制該麥克風陣列31朝該講者方位進行語音提取以得到一個語音訊號。此外，該語音提取模組36會經由該第一通訊模組32對該耳機裝置4無線發送該語音訊號。Thevoice extraction module 36 has a built-invoice tracking mode 361 and animage tracking mode 362. When thevoice tracking mode 361 is activated, thevoice extraction module 36 triggers themicrophone array 31 to receive audio, and triggers the voice Thetracking module 35 locates and obtains the direction of the voice source, and then thevoice extraction module 36 uses beamforming technology to control themicrophone array 31 to perform voice extraction in the direction of the voice source to obtain a voice signal; theimage tracking mode 362 is activated At this time, thevoice extraction module 36 triggers the image capturingmodule 33 to capture the image of the speaker, and triggers thespeaker tracking module 34 to analyze the image of the speaker to locate the speaker's location, and then, Thevoice extraction module 36 uses beamforming technology to control themicrophone array 31 to perform voice extraction toward the speaker to obtain a voice signal. In addition, thevoice extraction module 36 wirelessly transmits the voice signal to theearphone device 4 via thefirst communication module 32.

該耳機裝置4包括一個用以供該聽者900配戴在雙耳的耳機本體41，及一個設置在該耳機本體41且用以和該第一通訊模組32無線通訊的第二通訊模組42。該第二通訊模組42可無線接收該語音訊號，該耳機本體41可用以輸出該語音訊號以供該聽者900聆聽。在本實施例中，該耳機本體41為耳罩式耳機型態，可用以罩蓋在該聽者900雙耳，而可阻隔外界聲音，使該聽者900可專心聆聽來自該講者800的該語音訊號內容。Theearphone device 4 includes anearphone body 41 for thelistener 900 to wear on both ears, and a second communication module disposed on theearphone body 41 and used for wireless communication with thefirst communication module 32 42. Thesecond communication module 42 can receive the voice signal wirelessly, and theearphone body 41 can be used to output the voice signal for thelistener 900 to listen to. In this embodiment, theearphone body 41 is an over-ear earphone type, which can be used to cover both ears of thelistener 900, and can block external sounds, so that thelistener 900 can listen to thespeaker 800 attentively. The content of the voice signal.

本發明注意力集中輔助系統200架設使用時，可將該收音裝置3設置在該講台700，使該影像擷取模組33的影像擷取方向與該麥克風陣列31的收音方向都朝向該書寫板701方向，並使該耳機裝置4供配戴在該聽者900頭部而罩蓋雙耳，且使該收音裝置3與該耳機裝置4訊號連接。When the attention-focusingauxiliary system 200 of the present invention is installed and used, theradio device 3 can be set on thepodium 700 so that the image capturing direction of the image capturingmodule 33 and the sound receiving direction of themicrophone array 31 are both facing thewriting board 701 direction, and make theearphone device 4 to be worn on the head of thelistener 900 to cover both ears, and make theradio device 3 and theearphone device 4 signal connection.

初始使用時，可操作該講者追蹤模組34以透過該影像擷取模組33擷取預定之講者800的人物影像，或者透過其它輸入介面將講者800的人物影像輸入該講者追蹤模組34，使該講者追蹤模組34的該講者特徵建立單元341可分析該講者800的人物影像以建立該講者影像特徵參數。In initial use, thespeaker tracking module 34 can be operated to capture the image of thepredetermined speaker 800 through theimage capturing module 33, or input the image of thespeaker 800 into the speaker tracking through other input interfaces Themodule 34 enables the speakerfeature creation unit 341 of thespeaker tracking module 34 to analyze the character image of thespeaker 800 to create the speaker image feature parameters.

接著，可根據使用需求，操作該語音提取模組36以選擇啟動該語音追蹤模式361或該影像追蹤模式362。該語音提取模組36啟動該語音追蹤模式361時，會觸發該麥克風陣列31進行收音，且會觸發該語音追蹤模組35分析該麥克風陣列31收音之聲音訊號中的語音成分，藉以得到該語音音源方向，然後，該語音提取模組36會透過波束成形技術控制該麥克風陣列31朝該語音音源方向進行語音提取。該語音提取模組36啟動該影像追蹤模式362時，則會觸發該影像擷取模組33擷取該講方影像，且會觸發該講者追蹤模組34根據該講者影像特徵參數分析該講方影像以定位得到該講者方位，然後，該語音提取模組36會透過波束成形技術控制該麥克風陣列31朝該講者方位進行語音提取。最後，再經由該第一通訊模組32將所得到之該語音訊號發送至該耳機裝置4。Then, thevoice extraction module 36 can be operated to select thevoice tracking mode 361 or theimage tracking mode 362 according to usage requirements. When thevoice extraction module 36 activates thevoice tracking mode 361, it will trigger themicrophone array 31 to receive sound, and thevoice tracking module 35 will be triggered to analyze the voice components in the sound signal received by themicrophone array 31 to obtain the voice Then, thevoice extraction module 36 controls themicrophone array 31 to perform voice extraction in the direction of the voice source through beamforming technology. When thevoice extraction module 36 activates theimage tracking mode 362, it triggers theimage capture module 33 to capture the speaker image, and triggers thespeaker tracking module 34 to analyze the speaker image characteristic parameters The speaker image is used to locate the speaker's location, and then thevoice extraction module 36 controls themicrophone array 31 to extract the speaker's location through beamforming technology. Finally, the obtained voice signal is sent to theearphone device 4 through thefirst communication module 32.

由於該耳機本體41是設置在該聽者900雙耳，除了可阻隔外界聲音，還可直接播放該講者800的講話內容供該聽者900聆聽，即便該聽者900轉頭看向別處，依然會清楚聽到該講者800的講話內容，所以有助於提高該聽者900對於講者800講話內容的注意力，並大幅降低周遭環境聲音對具有注意力不集中症狀的該聽者900的干擾程度。Since theearphone body 41 is set in both ears of thelistener 900, in addition to blocking external sounds, it can also directly play the speech content of thespeaker 800 for thelistener 900 to listen to, even if thelistener 900 turns his head and looks away, You can still hear the content of thespeaker 800 clearly, so it helps to improve thelistener 900’s attention to the content of thespeaker 800, and greatly reduces the surrounding environment sounds to thelistener 900 with inattention symptoms. The degree of interference.

參閱圖4、5、6，本發明注意力集中輔助系統200的第二實施例與該第一實施例差異處在於：該收音裝置3設計，且該注意力集中輔助系統200還包含一個用以供該聽者900隨身攜帶，並訊號連接在該收音裝置3與該耳機裝置4間的隨身裝置5。為方便說明，以下將僅針對本第二實施例與該第一實施例差異處進行描述。Referring to Figures 4, 5, and 6, the second embodiment of the attention-focusingassist system 200 of the present invention differs from the first embodiment in that theradio device 3 is designed, and the attention-focusingassist system 200 also includes a system for Aportable device 5 for thelistener 900 to carry with him and signally connected between theradio device 3 and theearphone device 4. For the convenience of description, only the differences between the second embodiment and the first embodiment will be described below.

在本第二實施例中，該收音裝置3包括一個機殼30，及設置在該機殼30上的一個麥克風陣列31、一個影像擷取模組33、一個語音追蹤模組35、一個語音提取模組36與一個第一通訊模組32。由於該麥克風陣列31、該影像擷取模組33與該語音追蹤模組35的功能與該第一實施例相同，所以不再詳述。In the second embodiment, theradio device 3 includes acasing 30, and amicrophone array 31, an image capturingmodule 33, avoice tracking module 35, and a voice extraction module disposed on thecasing 30.Module 36 and afirst communication module 32. Since the functions of themicrophone array 31, theimage capturing module 33 and thevoice tracking module 35 are the same as those of the first embodiment, they will not be described in detail.

該第一通訊模組32可透過目前已知的無線通訊技術來與該隨身裝置5進行無線通訊，可用以無線傳送該影像擷取模組33擷取之該講方影像與該講者800的人物影像至該隨身裝置5、傳送該語音提取模組36進行語音提取所得到該語音訊號至該隨身裝置5，以及接收該隨身裝置5發送的該講者方位。Thefirst communication module 32 can wirelessly communicate with theportable device 5 through the currently known wireless communication technology, and can wirelessly transmit the image of the speaker captured by theimage capture module 33 and thespeaker 800 The person image is sent to theportable device 5, the voice signal obtained by thevoice extraction module 36 for voice extraction is transmitted to theportable device 5, and the speaker position sent by theportable device 5 is received.

該語音提取模組36同樣內建有該語音追蹤模式361與該影像追蹤模式362，於啟動該語音追蹤模式361時，會觸發啟動該麥克風陣列31與該語音追蹤模組35，並控制該麥克風陣列31朝該語音音源方向進行語音提取；於啟動該影像追蹤模式362時，會觸發該影像擷取模組33擷取得到該講方影像，並透過該第一通訊模組32將該講方影像傳送至該隨身裝置5，以及接收該隨身裝置5對應回傳的該講者方位，並控制該麥克風陣列31朝該講者方位對應之方向進行語音提取。最後，再將所提取的該語音訊號傳送至該隨身裝置5。Thevoice extraction module 36 also has built-invoice tracking mode 361 andimage tracking mode 362. When thevoice tracking mode 361 is activated, themicrophone array 31 and thevoice tracking module 35 are triggered to activate and control the microphone Thearray 31 extracts the voice in the direction of the voice source; when theimage tracking mode 362 is activated, theimage capturing module 33 is triggered to capture the image of the speaker, and the speaker is obtained through thefirst communication module 32 The image is transmitted to theportable device 5, and the speaker's position corresponding to theportable device 5 is received, and themicrophone array 31 is controlled to extract voice in the direction corresponding to the speaker's position. Finally, the extracted voice signal is transmitted to theportable device 5.

該隨身裝置5可供該聽者900隨身攜帶或配戴，包括一個第三通訊模組51與一個講者追蹤模組34。該第三通訊模組51可與該第一通訊模組32無線通訊，該講者追蹤模組34同樣具有該講者特徵建立單元341、該講者特徵比對單元342與該講者追蹤單元343，會分析該第三通訊模組51接收之該講者的人物影像以建立並儲存該講者影像特徵參數，以及分析該第三通訊模組51接收之該講方影像以得到該講者方位，並經由該第三通訊模組51回傳該講者方位至該收音裝置3。此外，該第三通訊模組51會將接收自該收音裝置3的該語音訊號傳送至該耳機裝置4。Theportable device 5 can be carried or worn by thelistener 900 and includes athird communication module 51 and aspeaker tracking module 34. Thethird communication module 51 can wirelessly communicate with thefirst communication module 32, and thespeaker tracking module 34 also has the speakerfeature establishing unit 341, the speaker feature comparing unit 342, and thespeaker tracking unit 343. Analyze the speaker image received by thethird communication module 51 to create and store the speaker image characteristic parameters, and analyze the speaker image received by thethird communication module 51 to obtain the speaker The position, and the speaker position is returned to theradio device 3 via thethird communication module 51. In addition, thethird communication module 51 transmits the voice signal received from theradio device 3 to theearphone device 4.

由於目前的手機與平板電腦等行動裝置，以及可供隨身攜帶的筆記型電腦的功能都相當強大，所以實施時，可將該講者追蹤模組34以APP（mobile application）等軟體程式的方式實施在具備與該收音裝置3及該耳機裝置4進行通訊的行動裝置或筆記型電腦上，以構成該隨身裝置5。Since current mobile devices such as mobile phones and tablets, as well as portable laptops have very powerful functions, when implemented, thespeaker tracking module 34 can be used in the form of software programs such as APP (mobile application) It is implemented on a mobile device or a notebook computer equipped with theradio device 3 and theearphone device 4 to communicate with each other to form theportable device 5.

該耳機裝置4與該第一實施例相同，但該第二通訊模組42可透過有線通訊技術及/或無線通訊技術來與該第三通訊模組51訊號連接，可接收該第三通訊模組51傳送的該語音訊號，且該耳機本體41可出該語音訊號以供該聽者900聆聽，而同樣有助於提升該聽者900對於該講者800的注意力集中效果。Theearphone device 4 is the same as the first embodiment, but thesecond communication module 42 can be signal-connected to thethird communication module 51 through wired communication technology and/or wireless communication technology, and can receive the third communication module. The voice signal transmitted by thegroup 51 and theearphone body 41 can output the voice signal for thelistener 900 to listen to, which also helps to improve the concentration effect of thelistener 900 on thespeaker 800.

藉由以該隨身裝置5之該講者追蹤模組34進行該講者影像特徵參數的建立，以及分析該講方影像以得到該講者方位的設計，可將需要耗費較多訊號處理資源的影像處理功能自該收音裝置3獨立出來，一方面可加快影像分析處理速度，另一方面可使該收音裝置3僅具備語音處理功能，而有助於該收音裝置3的小型化。By using thespeaker tracking module 34 of theportable device 5 to establish the characteristic parameters of the speaker image, and analyze the speaker image to obtain the design of the speaker orientation, it is possible to eliminate the need to consume more signal processing resources. The image processing function is independent of theradio device 3, on the one hand, it can speed up the image analysis and processing speed, on the other hand, theradio device 3 can only have the voice processing function, which contributes to the miniaturization of theradio device 3.

必須特別說明的是，在上述兩個實施例中，使用環境是以講堂為例進行說明，但實施時不以此為限，亦可適用在其它不具有所述講台、書寫板的環境中，僅需將該收音裝置3設置在該講者800與該聽者900間，使該收音裝置3可朝該講者方向進行收音與影像擷取，並以該耳機裝置供該聽者900配戴，同樣可用以協助具有注意力不集中症狀的聽者注意聆聽該講者800的講話內容。It must be particularly noted that in the above two embodiments, the use environment is described by taking a lecture hall as an example, but it is not limited to this during implementation, and it can also be applied to other environments that do not have the podium and writing board. It is only necessary to install theradio device 3 between thespeaker 800 and thelistener 900, so that theradio device 3 can receive and capture images in the direction of the speaker, and use the earphone device for thelistener 900 to wear , Can also be used to assist listeners with inattention symptoms to pay attention to the content of thespeaker 800's speech.

綜上所述，透過在該講者800與該聽者900間設置該收音裝置3，並以該收音裝置3追蹤該講者800的語音方向或講者方位以進行語音提取的設計，以及以該耳機裝置4供配戴在該聽者900雙耳，而直接輸出該收音裝置3接收之講者800的語音訊號的設計，除了可阻隔降低周遭環境聲音對該聽者900的干擾，不論該聽者900視線是否偏離該講者800，該聽者900都會直接聽到該講者800的講話內容，而可用以協助具有注意力不集中症狀的該聽者900專注於該講者800的講話內容，且該講者800也可更有效率地透過語音協助該聽者900將注意力往該講台700方向集中。To sum up, by setting up theradio device 3 between thespeaker 800 and thelistener 900, and using theradio device 3 to track thespeaker 800’s voice direction or the speaker’s orientation, the design of voice extraction is performed, and Theearphone device 4 is designed to be worn in both ears of thelistener 900 and directly output the voice signal of thespeaker 800 received by theradio device 3, in addition to blocking and reducing the interference of ambient sound on thelistener 900, regardless of the Whether the line of sight of thelistener 900 deviates from thespeaker 800, thelistener 900 will directly hear the speech content of thespeaker 800, and can be used to assist thelistener 900 with inattention symptoms to focus on the speech content of thespeaker 800 , And thespeaker 800 can also assist thelistener 900 to focus on theplatform 700 more efficiently through voice.

此外，可進一步配合以該隨身裝置5分析該講方影像以追蹤該講者方位的設計，將影像處理功能自該收音裝置3獨立出來，使該收音裝置3可更進一步小型化，且可將該講者追蹤模組34以APP（mobile application）等軟體程式的方式實施在具備與該收音裝置3及該耳機裝置4進行通訊，且功能強大的行動裝置或筆記型電腦上以構成該隨身裝置5，有助於加快該講者方位的追蹤速度。因此，本發明注意力集中輔助系統200確實是一種有助於改善注意力不集中症狀的創新輔具，確實能達成本發明的目的。In addition, theportable device 5 can be further used to analyze the speaker's image to track the speaker's position, and the image processing function can be separated from theradio device 3, so that theradio device 3 can be further miniaturized and reduced Thespeaker tracking module 34 is implemented on a powerful mobile device or a notebook computer capable of communicating with theradio device 3 and theearphone device 4 in the form of APP (mobile application) and other software programs to form theportable device 5. It helps to speed up the tracking speed of the speaker's position. Therefore, theconcentration assist system 200 of the present invention is indeed an innovative assistive device that helps to improve the symptoms of inattention, and can indeed achieve the purpose of the invention.

惟以上所述者，僅為本發明的實施例而已，當不能以此限定本發明實施的範圍，凡是依本發明申請專利範圍及專利說明書內容所作的簡單的等效變化與修飾，皆仍屬本發明專利涵蓋的範圍內。However, the above are only examples of the present invention. When the scope of implementation of the present invention cannot be limited by this, all simple equivalent changes and modifications made in accordance with the scope of the patent application of the present invention and the content of the patent specification still belong to Within the scope covered by the patent of the present invention.

200····· 注意力集中輔助系統 3········ 收音裝置 30······ 機殼 31······ 麥克風陣列 311····· 麥克風 32······ 第一通訊模組 33······ 影像擷取模組 34······ 講者追蹤模組 341····· 講者特徵建立單元 342····· 講者特徵比對單元 343····· 講者追蹤單元 35······ 語音追蹤模組 36······ 語音提取模組 361····· 語音追蹤模式 362····· 影像追蹤模式 4········ 耳機裝置 41······ 耳機本體 42······ 第二通訊模組 5········ 隨身裝置 51······ 第三通訊模組 700····· 講台 701····· 書寫板 800····· 講者 900····· 聽者200·····Attention Assist System 3········Radio device 30······Chassis 31······Microphone Array 311·····Microphone 32······ Thefirst communication module 33······Image Capture Module 34······Speaker Tracking Module 341····· Speaker Characteristics Establishment Unit 342·····SpeakerFeature Comparison Unit 343·····Speaker Tracking Unit 35······Voice Tracking Module 36······Voice Extraction Module 361·····Voice Tracking Mode 362·····Image Tracking Mode 4········Headphone Device 41······Headphone body 42······ Thesecond communication module 5········Portable device 51······Third Communication Module 700·····Podium 701·····Writing Board 800·····Speaker 900····· Listener

本發明的其他的特徵及功效，將於參照圖式的實施方式中清楚地呈現，其中： 圖1是本發明注意力集中輔助系統的一個第一實施例設置在一個講堂時的示意圖； 圖2是該第一實施例的立體圖； 圖3是該第一實施例的功能方塊圖； 圖4是本發明注意力集中輔助系統的一個第二實施例設置在一個講堂時的示意圖； 圖5是該第二實施例的立體圖；及 圖6是該第二實施例的功能方塊圖。Other features and effects of the present invention will be clearly presented in the embodiments with reference to the drawings, in which: FIG. 1 is a schematic diagram of a first embodiment of the attention-concentration assisting system of the present invention when it is set in a lecture hall; Figure 2 is a perspective view of the first embodiment; Figure 3 is a functional block diagram of the first embodiment; FIG. 4 is a schematic diagram of a second embodiment of the concentration assist system of the present invention when it is set in a lecture hall; Figure 5 is a perspective view of the second embodiment; and Fig. 6 is a functional block diagram of the second embodiment.

200····· 注意力集中輔助系統 3········ 收音裝置 31······ 麥克風陣列 311····· 麥克風 32······ 第一通訊模組 33······ 影像擷取模組 34······ 講者追蹤模組 341····· 講者特徵建立單元 342····· 講者特徵比對單元 343····· 講者追蹤單元 35······ 語音追蹤模組 36······ 語音提取模組 361····· 語音追蹤模式 362····· 影像追蹤模式 4········ 耳機裝置 41······ 耳機本體 42······ 第二通訊模組200·····Attention Assist System 3········Radio device 31······Microphone Array 311·····Microphone 32······ Thefirst communication module 33······Image Capture Module 34······Speaker Tracking Module 341····· Speaker Characteristics Establishment Unit 342·····SpeakerFeature Comparison Unit 343·····Speaker Tracking Unit 35······Voice Tracking Module 36······Voice Extraction Module 361·····Voice Tracking Mode 362·····Image Tracking Mode 4········Headphone device 41······Headphone body 42······ The second communication module

Claims (10)

Translated fromChinese

一種注意力集中輔助系統，包含一個用以設置在一位講者與一位聽者間的收音裝置，及一個用以供該聽者配戴的耳機裝置，其中：該收音裝置包括一個麥克風陣列、一個第一通訊模組、一個語音追蹤模組、一個用以朝該講者一側進行影像擷取以得到一個講方影像的影像擷取模組，及一個可分析定位該講方影像中之人物以得到一個講者方位的講者追蹤模組，及一個語音提取模組，該麥克風陣列具有多個用以朝該講者一側收音的麥克風，該語音追蹤模組可分析該等麥克風收音得到之聲音訊號中的語音成分，以定位得到語音訊號最強的一個語音音源方向，該語音提取模組內建有一個語音追蹤模式與一個影像追蹤模式，於啟動該語音追蹤模式時，會以波束成形技術控制該麥克風陣列朝該語音音源方向進行語音提取以得到一個語音訊號，於啟動該影像追蹤模式時，會觸發該講者追蹤模組追蹤定位得到該講者方位，且會以波束成形技術控制該麥克風陣列朝該講者方位進行語音提取以得到一個語音訊號，並經由該第一通訊模組對該耳機裝置無線發送前述每一語音訊號；該耳機裝置包括一個用以無線接收該語音訊號之第二通訊模組，及一個用以供配戴於該聽者之雙耳且用以輸出該語音訊號的耳機本體。An attention concentration assisting system includes a radio device for setting between a speaker and a listener, and an earphone device for the listener to wear, wherein: the radio device includes a microphone array , A first communication module, a voice tracking module, an image capturing module for capturing images toward the speaker to obtain a speaker image, and an image capturing module that can analyze and locate the speaker image The character in order to obtain a speaker tracking module for the position of the speaker, and a voice extraction module. The microphone array has a plurality of microphones for receiving the voice toward the speaker. The voice tracking module can analyze the microphones The voice component in the sound signal obtained by the radio is used to locate the direction of the voice source with the strongest voice signal. The voice extraction module has a built-in voice tracking mode and an image tracking mode. When the voice tracking mode is activated, it will The beamforming technology controls the microphone array to perform voice extraction in the direction of the voice source to obtain a voice signal. When the image tracking mode is activated, the speaker tracking module will be triggered to track and locate the speaker, and beamforming will be performed The technology controls the microphone array to perform voice extraction toward the speaker to obtain a voice signal, and wirelessly transmits each voice signal to the headset device via the first communication module; the headset device includes a device for wirelessly receiving the voice The second communication module of the signal, and an earphone body for being worn on the ears of the listener and for outputting the voice signal.如請求項1所述的注意力集中輔助系統，其中，該講者追蹤模組包括一個講者特徵比對單元，及一個講者追蹤單元，該講者特徵比對單元可根據一個對應該講者的講者影像特徵參數分析該講方影像以識別得到對應該講者的一個講者影像，該講者追蹤單元會分析定位出該講者影像於該講方影像中的位置以得到該講者方位。The attention concentration assistance system according to claim 1, wherein the speaker tracking module includes a speaker feature comparison unit and a speaker tracking listYuan, the speaker feature comparison unit can analyze the speaker image according to a speaker image feature parameter corresponding to the speaker to identify a speaker image corresponding to the speaker, and the speaker tracking unit will analyze and locate the speaker image. The position of the speaker's image in the speaker's image to obtain the speaker's position.如請求項2所述的注意力集中輔助系統，其中，該講者特徵比對單元會分析出該講者影像的頭部影像區域，該講者追蹤單元會分析定位該講者影像的該頭部影像區域以得到該講者方位。The attention concentration assistance system according to claim 2, wherein the speaker feature comparison unit analyzes the head image area of the speaker image, and the speaker tracking unit analyzes and locates the head image area of the speaker image Part of the image area to get the speaker’s location.如請求項2或3所述的注意力集中輔助系統，其中，該講者追蹤模組可供操作輸入該講者的人物影像，且還包括一個會分析擷取所述人物影像的人物特徵以建立該講者影像特徵參數的講者特徵建立單元。The attention concentration assistance system according to claim 2 or 3, wherein the speaker tracking module is operable to input the character image of the speaker, and further includes a character feature that analyzes and captures the character image to The speaker feature creation unit that creates the speaker image feature parameters.一種注意力集中輔助系統，包含一個用以設置在一位講者與一位聽者間的收音裝置，及用以供該聽者攜帶的一個隨身裝置與一個耳機裝置，其中：該收音裝置包括一個麥克風陣列、一個第一通訊模組、一個用以朝該講者一側進行影像擷取以得到一個講方影像的影像擷取模組，及一個語音提取模組，該麥克風陣列具有多個用以朝該講者一側收音的麥克風，該語音提取模組會以波束成形技術控制該麥克風陣列朝該講方影像中的一個講者方位進行語音提取以得到一個語音訊號，該第一通訊模組會透過無線通訊技術將該講方影像與該語音訊號發送給該隨身裝置；該隨身裝置包括一個用以無線接收該講方影像與該語音訊號的第三通訊模組，及一個講者追蹤模組，該講者追蹤模組可分析該講方影像中之人物以定位得到該講者方位，並經由該第三通訊模組對該第一通訊模組對應回傳該講者方位，並透過有線及/或無線通訊技術對該耳機裝置發送該語音訊號；該耳機裝置包括一個用以接收該第三通訊模組發送之該語音訊號的第二通訊模組，及一個用以供配戴於該聽者之雙耳且用以輸出該語音訊號的耳機本體。An attention concentration assisting system includes a radio device for setting between a speaker and a listener, and a portable device and an earphone device for the listener to carry, wherein: the radio device includes A microphone array, a first communication module, an image capturing module for capturing images toward the speaker to obtain an image of the speaker, and a voice extracting module, the microphone array having a plurality of The microphone is used to pick up the sound toward the speaker. The voice extraction module uses beamforming technology to control the microphone array to perform voice extraction toward a speaker position in the speaker image to obtain a voice signal. The first communication The module sends the speaking image and the voice signal to the portable device through wireless communication technology; the portable device includes a device for wirelessly receiving the speaking image and the voice signalThe third communication module of the voice signal, and a speaker tracking module, the speaker tracking module can analyze the person in the image of the speaker to locate the position of the speaker, and the third communication module The first communication module correspondingly returns the speaker's position and sends the voice signal to the earphone device through wired and/or wireless communication technology; the earphone device includes a device for receiving the voice signal sent by the third communication module The second communication module and a headphone body for wearing on the listener's ears and for outputting the voice signal.如請求項5所述的注意力集中輔助系統，其中，該講者追蹤模組包括一個講者特徵比對單元，及一個講者追蹤單元，該講者特徵比對單元可根據一個對應該講者的講者影像特徵參數分析該講方影像以識別得到一個對應該講者的講者影像，該講者追蹤單元會分析該講者影像於該講方影像中的位置以定位得到該講者方位。The attention concentration assistance system according to claim 5, wherein the speaker tracking module includes a speaker feature comparison unit and a speaker tracking unit, and the speaker feature comparison unit can respond according to a speaker The speaker image feature parameters of the speaker analyze the speaker image to identify a speaker image corresponding to the speaker, and the speaker tracking unit analyzes the position of the speaker image in the speaker image to locate the speaker position.如請求項6所述的注意力集中輔助系統，其中，該講者特徵比對單元會分析出該講者影像的頭部影像區域，該講者追蹤單元會分析定位該講者影像的該頭部影像區域以得到該講者方位。The attention concentration assistance system according to claim 6, wherein the speaker feature comparison unit analyzes the head image area of the speaker image, and the speaker tracking unit analyzes and locates the head image area of the speaker image Part of the image area to get the speaker’s location.如請求項6或7所述的注意力集中輔助系統，其中，該講者追蹤模組可供操作輸入該講者的人物影像，且還包括一個會分析擷取所述人物影像的人物特徵以建立該講者影像特徵參數的講者特徵建立單元。The attention concentration assistance system according to claim 6 or 7, wherein the speaker tracking module is operable to input the character image of the speaker, and further includes a character feature that analyzes and captures the character image to The speaker feature creation unit that creates the speaker image feature parameters.如請求項8所述的注意力集中輔助系統，其中，該收音裝置還包括一個語音追蹤模組，該語音追蹤模組可分析該等麥克風收音得到之聲音訊號中的語音成分，以定位得到語音訊號最強的一個語音音源方向，該語音提取模組內建有一個語音追蹤模式與一個影像追蹤模式，於啟動該語音追蹤模式時，會觸發啟動該語音追蹤模組定位得到該語音音源方向，並對該語音音源方向進行語音提取以得到該語音訊號，於啟動該影像追蹤模式時，會觸發啟動該影像擷取模組擷取得到該講方影像，且會朝該講者方位進行語音提取以得到該語音訊號。The attention concentration assistance system according to claim 8, wherein the radio device further includes a voice tracking module, and the voice tracking module can analyze theThe voice component in the sound signal received by the microphone is used to locate the direction of the voice source with the strongest voice signal. The voice extraction module has a built-in voice tracking mode and an image tracking mode. When the voice tracking mode is activated, it will Trigger the activation of the voice tracking module to locate the voice source direction, and perform voice extraction on the voice source direction to obtain the voice signal. When the image tracking mode is activated, the image capturing module will be triggered to capture and obtain the voice signal. The image of the speaker, and voice extraction will be performed toward the speaker's position to obtain the voice signal.如請求項5、6或7所述的注意力集中輔助系統，其中，該收音裝置還包括一個語音追蹤模組，該語音追蹤模組可分析該等麥克風收音得到之聲音訊號中的語音成分，以定位得到語音訊號最強的一個語音音源方向，該語音提取模組內建有一個語音追蹤模式與一個影像追蹤模式，於啟動該語音追蹤模式時，會觸發該語音追蹤模組定位得到該語音音源方向，並對該語音音源方向進行語音提取以得到該語音訊號，於啟動該影像追蹤模式時，會觸發該講者追蹤模組定位得到該講者方位，且朝該講者方位進行語音提取以得到該語音訊號。The attention concentration assistance system according to claim 5, 6 or 7, wherein the radio device further includes a voice tracking module, and the voice tracking module can analyze the voice components in the sound signals received by the microphones, The direction of the voice source with the strongest voice signal is obtained by positioning. The voice extraction module has a built-in voice tracking mode and an image tracking mode. When the voice tracking mode is activated, the voice tracking module will be triggered to locate the voice source Direction, and perform voice extraction on the voice source direction to obtain the voice signal. When the image tracking mode is activated, the speaker tracking module will be triggered to locate the speaker’s location, and perform voice extraction toward the speaker’s location. Get the voice signal.

Images