专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP3314606A1 LANGUAGE MODEL SPEECH ENDPOINTING 有权
标题翻译：语言模型演讲内容
公开(公告)号：EP3314606A1
公开(公告)日：2018-05-02
申请号：EP16736343.1
申请日：2016-06-27
申请人： Amazon Technologies, Inc.
发明人： HOFFMEISTER, Bjorn , RASTROW, Ariya , LIU, Baiyang
IPC分类号： G10L25/87 , G10L15/183 , G10L25/78
CPC分类号： G10L15/22 , G10L15/18 , G10L15/183 , G10L15/26 , G10L25/87 , G10L25/93 , G10L2025/783
摘要： An automatic speech recognition (ASR) system detects an endpoint of an utterance using the active hypotheses under consideration by a decoder. The ASR system calculates the amount of non-speech detected by a plurality of hypotheses and weights the non-speech duration by the probability of each hypotheses. When the aggregate weighted non-speech exceeds a threshold, an endpoint may be declared.

2. 发明公开

EP3188183A1 SPEECH ENDPOINTING BASED ON WORD COMPARISONS 无效转让
标题翻译：基于词比较的语音修饰
公开(公告)号：EP3188183A1
公开(公告)日：2017-07-05
申请号：EP17152524.9
申请日：2015-04-17
申请人： Google Inc.
发明人： BUCHANAN, Michael , GUPTA, Pravir K. , TANDIONO, Christopher Bo
IPC分类号： G10L15/04 , G10L15/22
CPC分类号： G10L15/05 , G10L15/04 , G10L15/22 , G10L15/26 , G10L17/06 , G10L25/51 , G10L25/78 , G10L25/87 , G10L25/90
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.
摘要翻译：描述了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，用于基于单词比较的语音终点。在一个方面，一种方法包括获取话语的转录的动作。该动作还包括确定文本样本集合中的文本样本的数量作为第一值，所述文本样本集合（i）包括与转录相匹配的词语，以及（ii）不包括任何附加词语。所述动作还包括确定（i）包括与转录相匹配的词语，以及（ii）包括一个或多个附加词语的文本样本集合中的文本样本的量作为第二值。所述动作还包括至少基于比较第一值和第二值将话语分类为可能不完整的话语或不可能不完整的话语。

3. 发明公开

EP3111627A1 PERCEPTUAL CONTINUITY USING CHANGE BLINDNESS IN CONFERENCING 有权
标题翻译：华盛顿哥伦比亚特区
公开(公告)号：EP3111627A1
公开(公告)日：2017-01-04
申请号：EP15712202.9
申请日：2015-02-17
申请人： Dolby Laboratories Licensing Corporation
发明人： CARTWRIGHT, Richard J. , DICKINS, Glenn N.
IPC分类号： H04M3/56 , H04R3/00
CPC分类号： H04M3/568 , G10L15/08 , G10L21/02 , G10L25/78 , G10L25/87 , H04M3/563 , H04M2201/14 , H04R3/005 , H04R2420/01 , H04W52/0229 , Y02D70/23 , Y02D70/25
摘要： In an audio conferencing mixing system of the type taking a plurality of audio input streams of input audio information of conference participants, including mixing transition events and outputting a plurality of audio output streams including output audio information, a method of mixing the audio output streams so as to reduce the detectability of the mixing transition events, the method including the steps of (a) determining that a transition event is to occur; (b) determining that a masking trigger is to occur; (c) scheduling the transition event to substantially occur when the masking event occurs. Change blindness mechanism to mask changes in audio conference mix and maintain perceptual continuity.
摘要翻译：在采用会议参与者的输入音频信息的多个音频输入流的类型的音频会议混合系统中，包括混合转换事件并输出包括输出音频信息的多个音频输出流，将音频输出流混合的方法为了降低混合转移事件的可检测性，该方法包括以下步骤：（a）确定发生转移事件; （b）确定将发生掩蔽触发; （c）在屏蔽事件发生时调度转换事件基本上发生。改变失明机制，掩盖音频会议组合的变化，维持感知连续性。

4. 发明授权

EP2828850B1 AUDIO PROCESSING METHOD AND AUDIO PROCESSING APPARATUS 有权
标题翻译：音频处理和音频处理设备
公开(公告)号：EP2828850B1
公开(公告)日：2016-03-16
申请号：EP13714817.7
申请日：2013-03-21
申请人： Dolby Laboratories Licensing Corporation
发明人： DENG, Huiqun , SUN, Xuejing
IPC分类号： G10L21/0364 , H04S1/00
CPC分类号： H04S1/007 , G10L21/0364 , G10L25/87 , H04S2400/01 , H04S2400/05

5. 发明公开

EP2891151A1 METHOD AND DEVICE FOR VOICE ACTIVITY DETECTION 有权
标题翻译：方法和设备识别语言活动的
公开(公告)号：EP2891151A1
公开(公告)日：2015-07-08
申请号：EP13765821.7
申请日：2013-08-30
申请人： Telefonaktiebolaget LM Ericsson (PUBL)
发明人： SEHLSTEDT, Martin
IPC分类号： G10L25/78
CPC分类号： G10L25/87 , G10L19/00 , G10L19/012 , G10L21/02 , G10L25/78
摘要： In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus for voice activity detection (VAD). The VAD comprises creating a signal indicative of a primary VAD decision and determining hangover addition. The determination on hangover addition is made in dependence of a short term activity measure and/or a long term activity measure. A signal indicative of a final VAD decision is then created.

6. 发明授权

EP1818837B1 System for a speech-driven selection of an audio file and method therefor 有权
标题翻译：系统用于音频文件及其方法的语音控制的选择
公开(公告)号：EP1818837B1
公开(公告)日：2009-08-19
申请号：EP06002752.1
申请日：2006-02-10
申请人： Harman Becker Automotive Systems GmbH
发明人： Gerl, Franz S., Dr. , Willett, Daniel, Dr. , Brueckner, Raymond
IPC分类号： G06F17/30 , G10L11/00
CPC分类号： G10L25/48 , G10H1/0008 , G10H2210/046 , G10H2210/066 , G10H2210/076 , G10H2210/081 , G10H2240/135 , G10H2240/141 , G10L25/87

7. 发明授权

EP1780704B1 Voice signal detection system and method 有权
标题翻译：用于语音检测方法和装置
公开(公告)号：EP1780704B1
公开(公告)日：2008-01-23
申请号：EP06122828.4
申请日：2006-10-24
申请人： Samsung Electronics Co., Ltd.
发明人： Kim, Hyun-Soo c/o Samsung Electronics Co., Ltd.
IPC分类号： G10L11/02 , H03G3/34 , H04R29/00
CPC分类号： G10L25/87 , G10L2025/783

8. 发明公开

EP1747553A4 DETECTION OF END OF UTTERANCE IN SPEECH RECOGNITION SYSTEM 审中-公开
标题翻译：检测表达的语音识别系统结束
公开(公告)号：EP1747553A4
公开(公告)日：2007-11-07
申请号：EP05739485
申请日：2005-05-10
申请人： NOKIA CORP
发明人： LAHTI TOMMI
IPC分类号： G10L11/02 , G10L15/14
CPC分类号： G10L25/87
摘要： The present invention relates to speech recognition systems, especially to arranging detection of end-of utterance in such systems. A speech recognizer of the system is configured to determine whether recognition result determined from received speech data is stabilized. The speech recognizer is configured to process values of best state scores and best token scores associated with frames of received speech data for end of utterance detection purposes. Further, the speech recognizer is configured to determine whether end of utterance is detected or not, based on the processing, if the recognition result is stabilized.

9. 发明公开

EP1771840A1 SPEECH END-POINTER 无效转让
标题翻译：地址结束指针
公开(公告)号：EP1771840A1
公开(公告)日：2007-04-11
申请号：EP06721766.1
申请日：2006-04-03
申请人： QNX Software Systems (Wavemakers), Inc.
发明人： HETHERINGTON, Phil , ESCOTT, Alex
IPC分类号： G10L11/02 , G10L15/20
CPC分类号： G10L25/87
摘要： A rule-based end-pointer isolates spoken utterances contained within an audio stream from background noise and non-speech transients. The rule-based end-pointer includes a plurality of rules to determine the beginning and/or end of a spoken utterance based on various speech characteristics. The rules may analyze an audio stream or a portion of an audio stream based upon an event, a combination of events, the duration of an event, or a duration relative to an event. The rules may be manually or dynamically customized depending upon factors that may include characteristics of the audio stream itself, an expected response contained within the audio stream, or environmental conditions.

10. 发明公开

EP1456837A1 VERFAHREN UND VORRICHTUNG ZUR SPRACHERKENNUNG 有权
标题翻译：方法和设备的语音识别
公开(公告)号：EP1456837A1
公开(公告)日：2004-09-15
申请号：EP01988071.5
申请日：2001-12-21
申请人： Telefonaktiebolaget LM Ericsson (publ)
发明人： DOBLER, Stefan
IPC分类号： G10L15/22 , G10L11/02
CPC分类号： G10L25/87 , G10L15/22
摘要： The invention relates to a method and device for recognition of words and pauses from a voice signal. Words (Wi) and pauses (Ti) spoken in a series are collated as belonging to a word group, once one of the pauses (Ti) exceeds a threshold value (TG). Stored references (Rj) are allocated for the voice signal of the word groups and, on exceeding the threshold (TG), a display of the result of the allocation occurs. Parameters are determined from the voice signal, corresponding to the time of the transitions between regions with speech and regions without and the threshold value (TG) then modified depending on said parameters.

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