专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

101. 发明授权

EP3026667B1 METHOD AND ELECTRONIC DEVICE FOR VOICE RECOGNITION 有权
标题翻译： VERFAHREN UND ELEKTRONISCHE VORRICHTUNG ZUR SPRACHERKENNUNG
公开(公告)号：EP3026667B1
公开(公告)日：2017-06-07
申请号：EP15195699
申请日：2015-11-20
申请人： SAMSUNG ELECTRONICS CO LTD
发明人： LEE TAE-JIN , LEE SANG-HOON , CHAKLADAR SUBHOJIT
IPC分类号： G10L15/22 , G06F1/32 , G10L15/08
CPC分类号： G10L15/22 , G06F1/3215 , G06F1/3231 , G06F1/324 , G06F1/3265 , G06F1/3293 , G06F3/167 , G10L2015/088 , G10L2015/223 , Y02D10/122 , Y02D10/126 , Y02D10/153 , Y02D10/173
摘要： Disclosed are a method and electronic device for voice recognition. The voice recognition method includes recognizing, in a first processor using low power mode, a voice signal inputted through a microphone, entering an active state and performing voice recording in a second processor if the recognized voice signal is a previously set keyword,, and performing voice recognition in the second processor if the end of a voice input is determined during the voice recording.
摘要翻译：公开了一种用于语音识别的方法和电子设备。该语音识别方法包括：在使用低功率模式的第一处理器中，如果识别的语音信号是预先设置的关键字，则识别通过麦克风输入的语音信号，进入活动状态并且在第二处理器中执行语音记录，如果在语音记录期间确定语音输入的结束，则在第二处理器中进行语音识别。

102. 发明公开

EP3139265A1 HANDSFREE DEVICE WITH CONTINUOUS KEYWORD RECOGNITION 无效转让
标题翻译：新西兰麻省理工学院
公开(公告)号：EP3139265A1
公开(公告)日：2017-03-08
申请号：EP16188850.8
申请日：2013-09-19
申请人： Google Inc.
发明人： STRACKE, John Richard Jr
IPC分类号： G06F3/16 , H04M1/60 , G10L15/30 , G10L15/08 , H04R1/10
CPC分类号： G10L15/08 , G06F3/167 , G10L15/30 , G10L2015/088 , H04M1/6066 , H04M2250/02 , H04M2250/74 , H04R1/1091 , H04R2201/107 , H04R2201/109 , H04R2420/07
摘要： A handsfree device, which is coupled to a data processing device, may be operable to monitor at least one audio stream for occurrence of at least one keyword. Upon recognition of the at least one keyword, the handsfree device may send audio data received after the recognition of the at least one keyword to a second device for processing by a voice interface included in the second device.
摘要翻译：耦合到数据处理设备的免提设备可以用于监视至少一个音频流以发生至少一个关键字。在识别出至少一个关键字后，免提装置可以在将至少一个关键字识别之后接收到的音频数据发送到第二装置，以便由包括在第二装置中的语音接口进行处理。

103. 发明公开

EP3047481A4 LOCAL AND REMOTE SPEECH PROCESSING 审中-公开
标题翻译： LOKALE UND ENTFERNTE SPRACHVERARBEITUNG
公开(公告)号：EP3047481A4
公开(公告)日：2017-03-01
申请号：EP14846698
申请日：2014-09-09
申请人： AMAZON TECH INC
发明人： STROM NIKKO , VANLUND PETER SPALDING , HOFFMEISTER BJORN
IPC分类号： G10L15/30 , G10L15/00 , G10L15/08 , G10L15/22 , G10L15/32
CPC分类号： G10L15/22 , G10L15/30 , G10L15/32 , G10L2015/088 , G10L2015/223
摘要： A user device may be configured to detect a user-uttered trigger expression and to respond by interpreting subsequent words or phrases as commands. The commands may be recognized by sending audio containing the words or phrases to a remote service that is configured to perform speech recognition. Certain commands may be designated as local commands and may be detected locally rather than relying on the remote service. Upon detection of the trigger expression, audio is streamed to the remote service and also analyzed locally to detect utterances of local commands. Upon detecting a local command, a corresponding function is immediately initiated, and subsequent activities or responses by the remote service are canceled or ignored.
摘要翻译：用户设备可以被配置为检测用户发出的触发表达式并且通过将后续的单词或短语解释为命令来进行响应。可以通过将包含单词或短语的音频发送到被配置为执行语音识别的远程服务来识别命令。某些命令可以被指定为本地命令，并且可以被本地检测而不是依赖于远程服务。在检测到触发表达式时，将音频流传输到远程服务，并在本地进行分析以检测本地命令的发声。在检测到本地命令时，立即启动相应的功能，并且远程服务的后续活动或响应被取消或忽略。

104. 发明公开

EP3125234A1 INDIVIDUALIZED HOTWORD DETECTION MODELS 有权转让
标题翻译：个性化的热点检测模型
公开(公告)号：EP3125234A1
公开(公告)日：2017-02-01
申请号：EP16186281.8
申请日：2016-07-12
申请人： Google Inc.
发明人： Guevara, Raziel Alvarez
IPC分类号： G10L15/06 , G10L15/08 , G10L15/07
CPC分类号： G10L17/04 , G10L15/02 , G10L15/063 , G10L15/07 , G10L15/075 , G10L15/1815 , G10L17/06 , G10L17/08 , G10L17/18 , G10L17/24 , G10L2015/0638 , G10L2015/088
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for presenting notifications in a system. In one aspect, a method includes actions of obtaining enrollment acoustic data representing an enrollment utterance spoken by a user, obtaining a set of candidate acoustic data representing utterances spoken by other users, determining, for each candidate acoustic data of the set of candidate acoustic data, a similarity score that represents a similarity between the enrollment acoustic data and the candidate acoustic data, selecting a subset of candidate acoustic data from the set of candidate acoustic data based at least on the similarity scores, generating a detection model based on the subset of candidate acoustic data, and providing the detection model for use in detecting an utterance spoken by the user.
摘要翻译：包括编码在计算机存储介质上的计算机程序的方法，系统和装置，用于在系统中呈现通知。在一个方面，一种方法包括以下动作：获取表示用户说出的注册话语的注册声学数据，获得表示由其他用户讲话的话语的一组候选声学数据，针对该组候选声学数据的每个候选声学数据，表示登记声学数据与候选声学数据之间的相似性的相似性分数，至少基于相似性分数从该组候选声学数据中选择候选声学数据的子集，基于子集候选声学数据，并提供用于检测用户说出的话语的检测模型。

105. 发明授权

EP2817800B1 MODIFIED MEL FILTER BANK STRUCTURE USING SPECTRAL CHARACTERISTICS FOR SOUND ANALYSIS 有权
标题翻译：随着对声音分析光谱特性改进的梅尔滤波器结构
公开(公告)号：EP2817800B1
公开(公告)日：2016-10-19
申请号：EP13751343.8
申请日：2013-02-11
申请人： Tata Consultancy Services Limited
发明人： JAIN, Jitendra , SINHA, Aniruddha
IPC分类号： G10L15/08 , G10L25/51 , G10L19/02 , G10L25/18
CPC分类号： G10L19/02 , G10L25/18 , G10L25/51

106. 发明公开

EP3014614A1 COMPUTER SYSTEM EMPLOYING SPEECH RECOGNITION FOR DETECTION OF NON-SPEECH AUDIO 审中-公开
标题翻译：具有语音识别计算机系统用于识别。NOT语言学AUDIO
公开(公告)号：EP3014614A1
公开(公告)日：2016-05-04
申请号：EP14740112.9
申请日：2014-06-26
申请人： Citrix Systems Inc.
发明人： THAPLIYAL, Ashish V. , ALEXANDROV, Albert
IPC分类号： G10L25/84 , G10L25/78 , G10L15/08
CPC分类号： G10L25/51 , G10L15/08 , G10L25/78 , G10L25/84 , H04L12/1827 , H04M3/567 , H04M3/568 , H04M2203/2027 , H04N7/15
摘要： A computer system executing a computer audio application such as video conferencing applies audio detection and speech recognition to an input audio stream to generate respective audio detection and speech recognition signals. A function is applied to the audio detection and speech recognition signals to generate a non-speech audio detection signal identifying presence of non-speech audio in the input audio stream when the audio detection signal is asserted and the speech recognition signal is not asserted. A control or indication action is performed in the computer system based on assertion of the non-speech audio detection signal.

107. 发明公开

EP2994911A1 ADAPTIVE AUDIO FRAME PROCESSING FOR KEYWORD DETECTION 有权
标题翻译：自适应音频帧处理中的关键单词识别
公开(公告)号：EP2994911A1
公开(公告)日：2016-03-16
申请号：EP14727131.6
申请日：2014-04-24
申请人： Qualcomm Incorporated
发明人： LEE, Minsub , KIM, Taesu , HWANG, KyuWoong , KIM, Sungwoong , JIN, Minho
IPC分类号： G10L15/22 , G10L15/08
CPC分类号： G10L15/08 , G10L15/183 , G10L15/22 , G10L15/32
摘要： A method of detecting a target keyword from an input sound for activating a function in a mobile device is disclosed. In this method, a first plurality of sound features is received in a buffer, and a second plurality of sound features is received in the buffer. While receiving each of the second plurality of sound features in the buffer, a first number of the sound features are processed from the buffer. The first number of the sound features includes two or more sound features. Further, the method may include determining a keyword score for each of the processed sound features and detecting the input sound as the target keyword if at least one of the keyword scores is greater than a threshold score.

108. 发明授权

EP2774144B1 ENHANCED STABILITY PREDICTION FOR INCREMENTALLY GENERATED SPEECH RECOGNITION HYPOTHESES 有权转让
标题翻译：提高稳定性预测渐进生成的语音识别假设
公开(公告)号：EP2774144B1
公开(公告)日：2016-01-06
申请号：EP12748820.3
申请日：2012-08-13
申请人： Google Inc.
发明人： MCGRAW, Ian C. , GRUENSTEIN, Alexander H.
IPC分类号： G10L15/08 , G10L15/22
CPC分类号： G03F7/70708 , G03F7/707 , G03F7/70875 , G03F7/70908 , G10L15/08 , G10L2015/223 , H01L21/6831

109. 发明授权

EP2680165B1 System and method to perform textual queries on voice communications 有权
标题翻译：系统和方法进行语音通信的文本请求
公开(公告)号：EP2680165B1
公开(公告)日：2016-01-06
申请号：EP12382256.1
申请日：2012-06-28
申请人： JaJah Ltd , Telefónica, S.A.
发明人： Neystadt, John , Urdiales Delgado, Diego
IPC分类号： G06F17/30 , G10L25/54 , G10L15/08 , G10L15/26 , G10L15/32 , G10L15/02
CPC分类号： G06F17/30867 , G06F17/30312 , G06F17/3053 , G06F17/30746 , G10L15/08 , G10L15/26 , G10L15/32 , G10L25/54 , G10L2015/025 , G10L2015/088
摘要： Methods and systems to perform textual queries on voice communications. The system comprises an index service for storing a plurality of audio content data sets for a plurality of voice communications, the plurality of audio content data sets comprising at least three audio content data sets for each voice communication, the at least three audio content data sets comprising a first audio content data set generated using a text-to-speech conversion technique, a second audio content data set generated using a phoneme lattice technique, and a third audio content data set generated using a keyword identification technique. The system also comprises a search engine configured to: receive search criteria from a user, the search criteria comprising at least one keyword; search each of the first, second and third audio content data sets for at least a portion of the plurality of voice communications to identify voice communications matching the search criteria; and combine the voice communications identified by each search to produce a combined list of identified voice communications.

110. 发明授权

EP1652173B1 Method and system for processing speech 有权转让
标题翻译：方法和系统语音处理
公开(公告)号：EP1652173B1
公开(公告)日：2015-12-30
申请号：EP03739921.9
申请日：2003-06-30
申请人： Chemtron Research LLC
发明人： ROY, Philippe
IPC分类号： G10L15/08 , G10L15/187
CPC分类号： G10L15/1822 , G10L15/08 , G10L2015/025
摘要： A system and method related to a new approach to speech recognition that reacts to concepts conveyed through speech. In its fullest implementation, the system and method shifts the balance of power in speech recognition from straight sound recognition and statistical models to a more powerful and complete approach determining and addressing conveyed concepts. This is done by using a probabilistically unbiased multi-phoneme recognition process, followed by a phoneme stream analysis process that builds the list of candidate words derived from recognized phonemes, followed by a permutation analysis process that produces sequences of candidate words with high potential of being syntactically valid, and finally, by processing targeted syntactic sequences in a conceptual analysis process to generate the utterance's conceptual representation that can be used to produce an adequate response. The invention can be employed for a myriad of applications, such as improving accuracy or automatically generating punctuation for transcription and dictation, word or concept spotting in audio streams, concept spotting in electronic text, customer support, call routing and other command/response scenarios.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式