-
31.发明公开SPEECH ENHANCEMENT METHOD AND APPARATUS FOR SAME 审中-公开SPRACHVERBESSERUNGSVERFAHREN UND VORRICHTUNGDAFÜR
公开(公告)号：EP3002753A1
公开(公告)日：2016-04-06
申请号：EP14807150.9
申请日：2014-05-30
发明人： CHO, Jae-youn , CUI, Weiwei , LEE, Seung-yeol
IPC分类号： G10L21/02
CPC分类号： G10L25/78 , G10L15/25 , G10L21/0208 , G10L21/0216 , G10L2021/02166 , H04R1/326
摘要： A speech enhancement method including: estimating a direction of a speaker by using an input signal, generating direction information indicating the estimated direction, detecting speech of a speaker based on a result of the estimating a direction, and enhancing the speech of the speaker by using the direction information of the estimating of a direction based on a result of the detecting of speech.
摘要翻译： 一种语音增强方法，包括：通过使用输入信号来估计扬声器的方向，产生指示估计方向的方向信息，基于估计方向的结果来检测讲话者的语音，以及通过使用 基于语音检测结果的方向估计的方向信息。
-
公开(公告)号：EP2859547A4
公开(公告)日：2016-01-06
申请号：EP13822547
申请日：2013-07-26
发明人： LEE DONGYEOL , SUH SANGBUM
摘要： Provided are a method and an apparatus for performing exact start and end recognition of voice based on video recognition. The method includes determining whether a speech starts based on at least one of first video and audio data before conversion into a voice recognition mode, converting into the voice recognition mode and generating second audio data including a voice command, when it is determined that speech starts, and determining whether the speech is terminated based on at least one of second video and audio data after conversion into the voice recognition mode.
-
公开(公告)号：EP2859547A1
公开(公告)日：2015-04-15
申请号：EP13822547.9
申请日：2013-07-26
发明人： LEE, Dongyeol , SUH, Sangbum
摘要： Provided are a method and an apparatus for performing exact start and end recognition of voice based on video recognition. The method includes determining whether a speech starts based on at least one of first video and audio data before conversion into a voice recognition mode, converting into the voice recognition mode and generating second audio data including a voice command, when it is determined that speech starts, and determining whether the speech is terminated based on at least one of second video and audio data after conversion into the voice recognition mode.
-
公开(公告)号：EP2795616A1
公开(公告)日：2014-10-29
申请号：EP11802081.7
申请日：2011-12-20
发明人： KJØLERBAKKEN, Morgan
CPC分类号： G10L15/02 , G06F3/16 , G10L15/25 , G10L2015/025 , G10L2021/02166
摘要： A method and system for speech recognition defined by using a microphone array that is directed to the face of a person speaking. Reading/scanning the output from the microphone array in order to determine which part of a face sound is emitting from. Using this information as input to a speech recognition system for improving speech recognition.
-
35.发明公开Mobile terminal supporting a voice talk function 审中-公开TragbaresEndgerätzumUnterstützeneiner Sprachfunktion
公开(公告)号：EP2765762A1
公开(公告)日：2014-08-13
申请号：EP14154157.3
申请日：2014-02-06
发明人： Ahn, Jihyun , Kim, Sora , Kim, Jinyong , Kim, Hyunkyoung , Kim, Heewoon , Ahn, Yumi
CPC分类号： G10L15/1822 , G06F3/167 , G06K9/00308 , G10L15/22 , G10L15/25 , G10L2015/226 , H04M1/72569 , H04M2250/52 , H04M2250/74
摘要： A voice talk function-enabled terminal and voice talk control method. The terminal comprises a display unit; an audio processing unit; and a control unit configured to: select content corresponding to a first criterion associated with a user in response to a user input; determine a content output scheme based on a second criterion associated with the user; and output the selected content through at least one of the display unit and the audio processing unit according to the content output scheme.
摘要翻译： 语音通话功能终端和语音通话控制方式。 终端包括显示单元; 音频处理单元; 以及控制单元，被配置为：响应于用户输入，选择与用户相关联的第一准则对应的内容; 基于与用户相关联的第二标准来确定内容输出方案; 并且根据内容输出方案通过显示单元和音频处理单元中的至少一个输出所选择的内容。
-
36.发明授权CHANGE INFORMATION RECOGNITION DEVICE AND CHANGE INFORMATION RECOGNITION METHOD 有权变更信息检测装置及变更信息检测方法
公开(公告)号：EP1619660B1
公开(公告)日：2014-05-07
申请号：EP04726766.1
申请日：2004-04-09
发明人： FUNAYAMA, Ryuji
CPC分类号： G10L15/25 , G06K9/00335
-
37.发明公开Method and apparatus for performing microphone beamforming 有权Verfahren und Vorrichtung zurDurchführungeiner Mikrofonstrahlenbildung
公开(公告)号：EP2428951A2
公开(公告)日：2012-03-14
申请号：EP11180609.7
申请日：2011-09-08
发明人： Cho, Sung-jae , Kim, Hyun-Soo
CPC分类号： G10L21/00 , G06K9/00335 , G10L15/25 , G10L17/00 , G10L2021/02166 , H04R1/406 , H04R29/005 , H04R2430/20
摘要： A method and apparatus for performing microphone beamforming. The method includes recognizing a speech of a speaker, searching for a previously stored image associated with the speaker, searching for the speaker through a camera based on the image, recognizing a position of the speaker, and performing microphone beamforming according to the position of the speaker.
摘要翻译： 一种用于执行麦克风波束成形的方法和装置。 该方法包括识别扬声器的语音，搜索与扬声器相关联的先前存储的图像，基于图像通过相机搜索扬声器，识别扬声器的位置，以及根据所述扬声器的位置来执行麦克风波束形成 扬声器。
-
公开(公告)号：EP1881484B1
公开(公告)日：2009-08-05
申请号：EP07021669.2
申请日：2004-04-09
发明人： Funayama, Ryuji
CPC分类号： G10L15/25 , G06K9/00335
-
39.发明授权Learning method and device, mobile communication terminal and information recognition system based on the analysis of user articulation movements during speech 有权根据一个讲用户的语音器官的运动的分析学习方法和装置，移动通信终端和信息识别系统
公开(公告)号：EP1336947B1
公开(公告)日：2007-08-29
申请号：EP03003781.6
申请日：2003-02-19
申请人： NTT DoCoMo, Inc.
发明人： Manabe, Hiroyuki, I. P. Dept. NTT DoCoMo, Inc. , Hiraiwa, Akira, I. P. Dept. NTT DoCoMo, Inc. , Sugimura, Toshiaki, I. P. Dept. NTT DoCoMo, Inc.
IPC分类号： G10L15/28
CPC分类号： G10L15/063 , G10L15/25 , G10L15/30
-
公开(公告)号：EP1624447A3
公开(公告)日：2006-02-15
申请号：EP05105074.8
申请日：2005-06-09
发明人： Laaser, Walter
IPC分类号： G10L15/24
CPC分类号： G10L15/25 , G10L2015/226
摘要： Haushaltgerät mit einer Funktionseinrichtung (10), mit einer Steuerungseinrichtung (14) und mit einer Bilderfassungseinrichtung (18) zum Erfassen eines Bildsignals (PS), welches gegenüber herkömmlichen Haushaltgeräten im Hinblick auf Barrierefreiheit weiterentwickelt ist, wobei das Gerät mit einer Erkennungseinrichtung (22) zur Verarbeitung und Auswertung eines Bildsignals (PS) ausgestattet ist, um hieraus eine vom Bediener gesprochene Lautfolge zu erkennen.
-
-
-
-
-
-
-
-
-
搜索结果
81 条记录 (耗时 0.023 秒)
