WO2007111162A1 - テキスト表示装置、テキスト表示方法およびプログラム - Google Patents
テキスト表示装置、テキスト表示方法およびプログラム Download PDFInfo
- Publication number
- WO2007111162A1 WO2007111162A1 PCT/JP2007/055374 JP2007055374W WO2007111162A1 WO 2007111162 A1 WO2007111162 A1 WO 2007111162A1 JP 2007055374 W JP2007055374 W JP 2007055374W WO 2007111162 A1 WO2007111162 A1 WO 2007111162A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- recognition
- word
- importance
- text
- recognition result
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/06—Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
- H04N21/440236—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
Definitions
- Text display device text display method and program
- the present invention relates to a text display device that displays text in synchronization with voice input, a text display method, and a program for causing a computer to execute the method.
- FIG. 5 is a block diagram showing a configuration example of a conventional caption display device.
- a conventional caption display device includes a voice input unit 201 for inputting voice, a storage unit 230 in which a recognition dictionary 203 for voice recognition is stored, and a voice recognition unit 202 for recognizing the input voice.
- the control unit 220 includes an output unit 204 for displaying text.
- the voice input unit 201 is represented by a microphone.
- the conventional caption display device shown in FIG. 5 generally performs speech recognition processing when a speaker's utterance is received, and displays a recognition result word or word string with a slight delay from the speech. If the next utterance has already started after the recognition result is displayed, the next recognition result may be displayed in the same manner after a certain period of time.
- FIG. 6 is a diagram showing a specific example of input voice and its recognition result.
- the mobile phone has the configuration shown in FIG.
- the cellular phone performs recognition processing for each section where the voice is detected, and displays the subtitles 502a to 502d in order for a certain period of time as the recognition result.
- the mobile phone displays each of the subtitles 502a to 502d for a certain period of time TO from time tl to t5. In this way, the recognized word or word string is displayed for a certain period of time or until the next recognition result is obtained! /.
- Patent Document 1 Japanese Patent Application Laid-Open No. 2002-342311
- the present invention has been made to solve the problems of the conventional techniques as described above, and is a text display device capable of efficiently transmitting information by voice to the user as text. It is an object to provide a display method and a program for causing a computer to execute the method.
- a text display device of the present invention includes a voice input unit for inputting voice, a storage unit storing a recognition dictionary for converting voice information into text,
- a recognition dictionary for converting voice information into text
- an output unit for displaying text and a word or a word string corresponding to the voice are recognized with reference to the recognition dictionary, and a recognition result including the word or the word string and its A control unit that obtains an importance level, calculates a display time of the recognition result corresponding to the importance level, and causes the output unit to display the recognition result for a time longer than the calculated display time.
- control unit is any one of the reliability of recognition of input speech, the word importance described in the recognition dictionary, and the word importance specified by the user 1 One or a combination thereof may determine the importance of the recognition result.
- control unit may recognize another recognition result from the calculation result of the display time.
- the recognition result that is determined to be displayed for a longer time than the recognition result is either underlined, highlighted, or changed in font, size, or color
- One or a combination of these may be displayed on the output unit.
- the recognition result is displayed on the output unit for a time longer than the time calculated according to the importance. Therefore, if a recognition result with a high degree of importance is displayed for a long time, important information can be easily transmitted to the user.
- a text display method of the present invention for achieving the above object is a text display method by an information processing apparatus for converting speech into text, and stores a recognition dictionary for converting speech information into text.
- a speech is input, a word or a word string corresponding to the speech is recognized with reference to the recognition dictionary, and a recognition result including the word or the word string and its importance are obtained.
- the display time of the recognition result is calculated corresponding to the importance, and the recognition result is displayed on the output unit for the calculated display time or longer.
- the text display method may be one of the reliability of the recognition of the input speech, the word importance described in the recognition dictionary, and the word importance specified by the user, or one of these.
- the importance of the recognition result may be determined by a combination of.
- the text display method may underline, highlight, or display a recognition result determined to be displayed for a longer time than the other recognition results from the display time calculation result. Any one of changing the size or color, or a combination of these may be highlighted and displayed on the output unit.
- a program of the present invention for achieving the above object is a program for causing a computer to execute processing for converting speech into text and displaying it, and for recognizing speech information for conversion into text.
- a step of storing a dictionary in a storage unit; a step of recognizing a word or a word string corresponding to the voice by referring to the recognition dictionary when a voice is input; and a recognition result including the word or the word string And a step of obtaining the importance level, a step of calculating a display time of the recognition result corresponding to the importance level, and a calculation And displaying the recognition result on the output unit for the display time or longer.
- the program may be based on one of the reliability of recognition of input speech, the word importance described in the recognition dictionary, and the word importance specified by the user, or a combination thereof.
- the method may include a step of determining the importance of the recognition result.
- the program draws an underline, highlights, or displays the recognition result determined to be displayed for a longer time than the other recognition results from the calculation result of the display time.
- any one of changing the size or color, or a step of emphasizing by a combination of these may be displayed on the output unit.
- the recognition result with high importance is displayed for a long time by giving priority to the recognition result, so that the important recognition result remains in the output unit even when the display screen is switched. Therefore, even if the place and time for displaying the recognition result are not sufficient, information can be efficiently transmitted to the user.
- FIG. 1 is a block diagram showing a configuration example of a text display device according to the present embodiment.
- FIG. 2 is a flowchart showing an operation procedure of the text display device of the present embodiment.
- FIG. 3 is a diagram illustrating a description example of a recognition dictionary according to the present embodiment.
- FIG. 4 is a diagram showing an example of input speech and recognition results of the present embodiment.
- FIG. 5 is a block diagram showing a configuration example of a conventional text display device.
- FIG. 6 is a diagram showing a specific example of input speech and recognition results in the conventional case.
- the text display device of the present invention obtains the recognition result recognized from the input speech and its importance, calculates the display time corresponding to the importance, and displays the recognition result for the calculated display time or longer. It is characterized by that.
- FIG. 1 is a block diagram showing an example of the configuration of the text display device of the present embodiment.
- the text display device recognizes the speech input unit 101 for inputting speech, the storage unit 130 storing the recognition dictionary 103, and the input speech using the recognition dictionary 103, and the recognition result.
- a speech recognition unit 202 that outputs a word or a word string and its importance
- a control unit 120 that includes a display time calculation unit 204 that calculates a display time from the importance
- an output unit 105 that displays a recognition result
- the control unit 120 causes the output unit 105 to display the display time and the recognition result calculated by the display time calculation unit 204 according to the importance.
- the control unit 120 has a CPU (Central Processing Unit) that executes predetermined processing according to a program and a memory for storing the program.
- the voice recognition unit 102 and the display time calculation unit 104 are virtually configured in the control unit 120 when the CPU executes a program.
- FIG. 2 is a flowchart showing the operation procedure of the text display device.
- step 301 when voice is input via the voice input means 101 (step 301) and the voice recognition means 102 receives voice data from the voice input means 101, it is stored in the storage unit 130.
- the speech is recognized with reference to the recognized recognition dictionary 103 (step 302).
- a recognition result including a word or a word string is output and its importance is obtained.
- the recognition result and its importance are output to the display time calculation means 104.
- the display time calculation unit 104 receives the recognition result and the importance level information from the voice recognition means 102
- the display time calculation unit 104 calculates the display time of the recognition result corresponding to the importance level (step 303).
- the control unit 120 causes the output unit 105 to display the display time and the recognition result calculated according to the importance (step 304).
- FIG. 3 is a diagram showing a description example of the recognition dictionary. As shown in FIG. 3, in the recognition dictionary 103, the importance of the word “RSS” is “3.0”, the importance of the word “site” is “1.5”, and the word “ It is described that the importance of “John” is “0.9”.
- the speech recognition means 102 When the speech recognition means 102 identifies a word or word string with reference to the recognition dictionary 103, the speech recognition means 102 reads the importance from the recognition dictionary 103, and the recognition result including the identified word or word string and information on the importance To the display time calculation means 104.
- Cw is a value indicating the word importance of the word w.
- p is a coefficient.
- An example of p is a display area dependent constant of the system.
- the display area-dependent constant is a value that is determined by restrictions on the screen display size. The smaller the screen display size, the smaller the value because there is no room in the place and time for displaying the recognition result.
- the control unit 120 highlights the recognition result with a high importance level, so that the recognition result is underlined with a high importance level. Displayed on the output unit 105. In this embodiment, it is assumed that the output unit 105 is highlighted when the display time of the recognition result is equal to or greater than the first threshold.
- the first threshold value is the time for the criterion for determining the force or power to be highlighted.
- the control unit 120 does not display the recognition result on the output unit 105 as a low importance if the display time of the recognition result does not reach the second threshold value.
- the second threshold is a time that is a criterion for determining whether or not to display the force.
- the first threshold and the second threshold are stored in advance in the storage unit 1 Stored in 30.
- FIG. 4 is a diagram showing an example of input speech and recognition results in this embodiment.
- the input voice information is the same as in the conventional case shown in FIG.
- the coefficient p in the above equation (1) is set to 3.0.
- the first threshold is set to 3.5 seconds
- the second threshold is set to 2.0 seconds.
- the standard subtitle switching period is set to 3.5 seconds.
- the speech recognition means 102 recognizes words or word strings by speech in order.
- the importance “3.0” is read from the recognition dictionary 103, and information about the word “RSS” and the importance “3.0” is passed to the display time calculation means 104.
- the display time calculation means 104 calculates the display time T1 of the word “13 ⁇ 43” from the above equation (1).
- the control unit 120 recognizes that the word “RSS highlighting target”. RSS is the information until “... is in circulation,” and after confirming what is highlighted, the subtitle 402a is displayed on the output unit 105.
- the voice recognition means 102 recognizes the voices up to "each" is continuing.
- the importance is obtained for each recognized word or word string, and is passed to the display time calculation means 104.
- the display time calculation means 104 calculates the display time for each word or word string.
- the display time of the word sequence “continued” is 1.5 seconds. This time is less than the second threshold.
- the word “RSS” displayed in the subtitle 402a is an object to be highlighted.
- the control unit 120 displays the subtitle 402a for 3.5 seconds and then instructs the output unit 105 to switch to the next subtitle, the display time of the word "RSS" in the subtitle 402a is set to 9 seconds. Because it is less than that, the word “RSS” is displayed in an underlined state. Further, the control unit 120 causes the output unit 105 to display the next subtitle 402b except for the word string “following”. In this way, subtitles 402b as shown in FIG.
- the voice recognition means 102 recognizes the next voice as "Weblog ". This is the same as described above.
- the display time calculation means 104 calculates the display time for each word or word string, based on the recognition result that also receives the voice recognition means 102 power, the information on its importance, and the above equation (1).
- the control unit 120 outputs the word “RSS” because the display time of the two subtitles 402a and 402b is 7 seconds, which is less than 9 seconds.
- the subtitle 402c is displayed, the word “RSS” remains highlighted. In this way, the caption 402c shown in FIG.
- the control unit 120 applies the word “ ⁇ ⁇ 1 0 ⁇ ” and the word string “site overview format” to the highlight object as in the case of the word “13 ⁇ 43”. Make a decision.
- the voice “newly proposed” is recognized by the voice recognition means 102, and the display time is displayed by the display time calculation means 104 for each word or word string. Calculated. Thereafter, the control unit 120 displays the next subtitle to the output unit 105 because the display time of the word “RSS” is 10.5 seconds, which is the sum of the three subtitle display times of subtitles 402a to 402c. When displaying, delete the word "RSS" from the display. On the other hand, since the word “We blogj” and the word string “site summary format” are newly highlighted, the control unit 120 sends the word “Weblog” and the word string “site summary format” to the output unit 105. Highlight. As a result, the subtitle 402d is displayed on the output unit 105 as shown in FIG.
- the display target and the display time of the recognition result are obtained in consideration of the level of importance and the display constraint, and the display screen where the text display location and time are not sufficient. Select the recognition result to be displayed on the screen. Even if the recognition results cannot be displayed in real time, the recognition results to be highlighted are displayed for a long time, and the recognition results with low importance are not displayed. Is possible.
- the recognition result “RSS” to be highlighted is displayed for three subtitle display times (total display time 10.5 seconds), but the recognition result “RSS” is displayed. When the time reaches 9 seconds, the recognition result “RSS” may be deleted from the display screen.
- the importance of the word or word string is described in advance in the recognition dictionary 103 as shown in FIG. However, it may be changed according to the user's profile. For example, even if a word is highly important when it is first registered in the recognition dictionary 103, if it is highlighted many times, the user can understand the meaning of that word. make low. You can specify a word with high importance by yourself or write a numerical value indicating the importance.
- the recognition result display time may be obtained using the recognition reliability instead of the word importance.
- the recognition reliability indicates the suitability between the speech data and the word or word string when the speech recognition means 102 refers to the recognition dictionary 103 and identifies the word or word string for the input speech. If the input speech is not clear ⁇ or if there are multiple registered words that are similar in reading, there is a high probability that the speech recognition means 102 will identify a word or word string that is different from the input speech. , Reliability is low. This is because the recognition result with low reliability may be misrecognized, and if such a recognition result is highlighted, the user may be confused.
- the importance of a word or a word string may be obtained by a combination of a numerical value described in advance in the recognition dictionary 103 as shown in FIG. 3 and the recognition reliability.
- the numerical value previously described in the recognition dictionary 103 is high, if the reliability of the recognition result is low, the possibility of misrecognition increases and the information is not displayed.
- misrecognition results with low reliability errors in information transmission can be reduced. As a result, the accuracy of information transmission to the user is improved.
- the importance of the word or the word string is obtained by any one of the importance registered in the recognition dictionary 103 in advance, the designation by the user, and the reliability of recognition, or a combination thereof.
- the recognition dictionary 103 in advance, the designation by the user, and the reliability of recognition, or a combination thereof.
- the recognition results “RSS” and “Weblog” are highlighted by highlighting words that are determined to have high importance and long display time.
- the font, size, or color of the target text may be changed! The target text may be highlighted.
- a combination of these methods may be used. As a result, the user can easily distinguish words having high importance and long display time from other words.
- the text display device of the present invention recognizes the input speech information, the text display device displays the recognition result on the output unit for a time calculated in accordance with the importance.
- the text display device of the present invention can be applied to uses such as caption display in TV broadcasting, videophone, and web conferences. Further, the present invention may be applied to a program for causing a computer to execute the text display method of the present invention.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- User Interface Of Digital Computer (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2008507433A JPWO2007111162A1 (ja) | 2006-03-24 | 2007-03-16 | テキスト表示装置、テキスト表示方法およびプログラム |
| US12/294,318 US20090287488A1 (en) | 2006-03-24 | 2007-03-16 | Text display, text display method, and program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2006082658 | 2006-03-24 | ||
| JP2006-082658 | 2006-03-24 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2007111162A1 true WO2007111162A1 (ja) | 2007-10-04 |
Family
ID=38541082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2007/055374 Ceased WO2007111162A1 (ja) | 2006-03-24 | 2007-03-16 | テキスト表示装置、テキスト表示方法およびプログラム |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20090287488A1 (ja) |
| JP (1) | JPWO2007111162A1 (ja) |
| CN (1) | CN101410790A (ja) |
| WO (1) | WO2007111162A1 (ja) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011099086A1 (ja) * | 2010-02-15 | 2011-08-18 | 株式会社 東芝 | 会議支援装置 |
| JP2012181358A (ja) * | 2011-03-01 | 2012-09-20 | Nec Corp | テキスト表示時間決定装置、テキスト表示システム、方法およびプログラム |
| JP2013174718A (ja) * | 2012-02-24 | 2013-09-05 | Toshiba Corp | 音声記録選択装置、音声記録選択方法及び音声記録選択プログラム |
| JP2019062332A (ja) * | 2017-09-26 | 2019-04-18 | 株式会社Jvcケンウッド | 表示態様決定装置、表示装置、表示態様決定方法及びプログラム |
| JP2022049984A (ja) * | 2020-09-17 | 2022-03-30 | Necソリューションイノベータ株式会社 | 出力方法 |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4957821B2 (ja) * | 2010-03-18 | 2012-06-20 | コニカミノルタビジネステクノロジーズ株式会社 | 会議システム、情報処理装置、表示方法および表示プログラム |
| CN102385861B (zh) * | 2010-08-31 | 2013-07-31 | 国际商业机器公司 | 一种用于从语音内容生成文本内容提要的系统和方法 |
| CN102566863B (zh) * | 2010-12-25 | 2016-07-27 | 上海量明科技发展有限公司 | 在即时通信工具中设置辅助区的方法及系统 |
| DE112012002190B4 (de) * | 2011-05-20 | 2016-05-04 | Mitsubishi Electric Corporation | Informationsgerät |
| CN102693094A (zh) * | 2012-06-12 | 2012-09-26 | 上海量明科技发展有限公司 | 即时通信中调整字符的方法、客户端及系统 |
| JP5921722B2 (ja) * | 2013-01-09 | 2016-05-24 | 三菱電機株式会社 | 音声認識装置および表示方法 |
| CN112599130B (zh) * | 2020-12-03 | 2022-08-19 | 安徽宝信信息科技有限公司 | 一种基于智慧屏的智能会议系统 |
| CN114360530B (zh) * | 2021-11-30 | 2024-08-27 | 北京罗克维尔斯科技有限公司 | 语音测试方法、装置、计算机设备和存储介质 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10123450A (ja) * | 1996-10-15 | 1998-05-15 | Sony Corp | 音声認識機能付ヘッドアップディスプレイ装置 |
| JPH10301927A (ja) * | 1997-04-23 | 1998-11-13 | Nec Software Ltd | 電子会議発言整理装置 |
| JP2006005861A (ja) * | 2004-06-21 | 2006-01-05 | Matsushita Electric Ind Co Ltd | 文字スーパー表示装置および文字スーパー表示方法 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030093790A1 (en) * | 2000-03-28 | 2003-05-15 | Logan James D. | Audio and video program recording, editing and playback systems using metadata |
| GB2323693B (en) * | 1997-03-27 | 2001-09-26 | Forum Technology Ltd | Speech to text conversion |
| US6839669B1 (en) * | 1998-11-05 | 2005-01-04 | Scansoft, Inc. | Performing actions identified in recognized speech |
| US7164753B2 (en) * | 1999-04-08 | 2007-01-16 | Ultratec, Incl | Real-time transcription correction system |
| US7953219B2 (en) * | 2001-07-19 | 2011-05-31 | Nice Systems, Ltd. | Method apparatus and system for capturing and analyzing interaction based content |
| JP2004304601A (ja) * | 2003-03-31 | 2004-10-28 | Toshiba Corp | Tv電話装置、tv電話装置のデータ送受信方法 |
| JP3945778B2 (ja) * | 2004-03-12 | 2007-07-18 | インターナショナル・ビジネス・マシーンズ・コーポレーション | 設定装置、プログラム、記録媒体、及び設定方法 |
| US7729478B1 (en) * | 2005-04-12 | 2010-06-01 | Avaya Inc. | Change speed of voicemail playback depending on context |
-
2007
- 2007-03-16 US US12/294,318 patent/US20090287488A1/en not_active Abandoned
- 2007-03-16 JP JP2008507433A patent/JPWO2007111162A1/ja active Pending
- 2007-03-16 CN CNA200780010487XA patent/CN101410790A/zh active Pending
- 2007-03-16 WO PCT/JP2007/055374 patent/WO2007111162A1/ja not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10123450A (ja) * | 1996-10-15 | 1998-05-15 | Sony Corp | 音声認識機能付ヘッドアップディスプレイ装置 |
| JPH10301927A (ja) * | 1997-04-23 | 1998-11-13 | Nec Software Ltd | 電子会議発言整理装置 |
| JP2006005861A (ja) * | 2004-06-21 | 2006-01-05 | Matsushita Electric Ind Co Ltd | 文字スーパー表示装置および文字スーパー表示方法 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011099086A1 (ja) * | 2010-02-15 | 2011-08-18 | 株式会社 東芝 | 会議支援装置 |
| JP2012181358A (ja) * | 2011-03-01 | 2012-09-20 | Nec Corp | テキスト表示時間決定装置、テキスト表示システム、方法およびプログラム |
| JP2013174718A (ja) * | 2012-02-24 | 2013-09-05 | Toshiba Corp | 音声記録選択装置、音声記録選択方法及び音声記録選択プログラム |
| JP2019062332A (ja) * | 2017-09-26 | 2019-04-18 | 株式会社Jvcケンウッド | 表示態様決定装置、表示装置、表示態様決定方法及びプログラム |
| JP2022049984A (ja) * | 2020-09-17 | 2022-03-30 | Necソリューションイノベータ株式会社 | 出力方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20090287488A1 (en) | 2009-11-19 |
| JPWO2007111162A1 (ja) | 2009-08-13 |
| CN101410790A (zh) | 2009-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2007111162A1 (ja) | テキスト表示装置、テキスト表示方法およびプログラム | |
| JP5064404B2 (ja) | モバイルデバイスにおける音声および代替入力手法の組み合わせ | |
| CN111312231B (zh) | 音频检测方法、装置、电子设备及可读存储介质 | |
| JP6751658B2 (ja) | 音声認識装置、音声認識システム | |
| CN106971723B (zh) | 语音处理方法和装置、用于语音处理的装置 | |
| US10553206B2 (en) | Voice keyword detection apparatus and voice keyword detection method | |
| US8868419B2 (en) | Generalizing text content summary from speech content | |
| JPWO2015098109A1 (ja) | 音声認識処理装置、音声認識処理方法、および表示装置 | |
| CN109036406A (zh) | 一种语音信息的处理方法、装置、设备和存储介质 | |
| KR20130135410A (ko) | 음성 인식 기능을 제공하는 방법 및 그 전자 장치 | |
| CN106250474A (zh) | 一种语音控制的处理方法及系统 | |
| WO2016110068A1 (zh) | 语音识别设备语音切换方法及装置 | |
| CN113763921B (zh) | 用于纠正文本的方法和装置 | |
| CN112863496B (zh) | 一种语音端点检测方法以及装置 | |
| US20250378286A1 (en) | Application Programming Interfaces For On-Device Speech Services | |
| US11217266B2 (en) | Information processing device and information processing method | |
| JP2008033198A (ja) | 音声対話システム、音声対話方法、音声入力装置、プログラム | |
| JP6260138B2 (ja) | コミュニケーション処理装置、コミュニケーション処理方法、及び、コミュニケーション処理プログラム | |
| CN110971505B (zh) | 一种通讯信息处理方法、装置、终端及计算机可读介质 | |
| CN115394297A (zh) | 一种语音识别方法、装置、电子设备及存储介质 | |
| US20080256071A1 (en) | Method And System For Selection Of Text For Editing | |
| CN108491183B (zh) | 一种信息处理方法和电子设备 | |
| CN114564265B (zh) | 有屏智能设备的交互方法、装置以及电子设备 | |
| US20200219482A1 (en) | Electronic device for processing user speech and control method for electronic device | |
| JP2020024310A (ja) | 音声処理システム及び音声処理方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 07738819 Country of ref document: EP Kind code of ref document: A1 |
|
| DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
| WWE | Wipo information: entry into national phase |
Ref document number: 2008507433 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 12294318 Country of ref document: US Ref document number: 200780010487.X Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 07738819 Country of ref document: EP Kind code of ref document: A1 |
|
| DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) |