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. 发明申请

US20180158450A1 SPEECH RECOGNITION APPARATUS AND SPEECH RECOGNITION METHOD 审中-公开
公开(公告)号：US20180158450A1
公开(公告)日：2018-06-07
申请号：US15825087
申请日：2017-11-28
申请人： Olympus Corporation
发明人： Hiroyuki TOKIWA , Kenta YUMOTO , Osamu NONAKA
IPC分类号： G10L15/02 , G10L25/57
CPC分类号： G10L15/02 , G06K9/00221 , G06K9/00335 , G10L15/25 , G10L25/57 , G10L2015/022 , G10L2015/025 , G10L2015/027
摘要： A speech recognition apparatus according to an embodiment includes a microphone that acquires an audio stream in which speech vocalized by a person is recorded, a camera that acquires an image data in which at least a mouth of the person is captured, and an operation element that recognizes speech including a consonant vocalized by the person, based on the audio stream, estimates the consonant vocalized by the person, based on the shape of the mouth of the person in the image data, and specifies the consonant based on the estimated consonant and the speech-recognized consonant.

2. 发明申请

US20170358293A1 PREDICTING PRONUNCIATIONS WITH WORD STRESS 审中-公开
公开(公告)号：US20170358293A1
公开(公告)日：2017-12-14
申请号：US15178719
申请日：2016-06-10
申请人： Google Inc.
发明人： Mason Vijay Chua , Kanury Kanishka Rao , Daniel Jacobus Josef van Esch
IPC分类号： G10L13/10 , G10L15/16 , G10L25/30 , G10L15/02 , G10L15/06 , G10L15/18
CPC分类号： G10L13/10 , G10L13/0335 , G10L13/047 , G10L13/08 , G10L15/02 , G10L15/063 , G10L15/16 , G10L15/1815 , G10L15/187 , G10L17/18 , G10L25/30 , G10L2015/027
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating word pronunciations. One of the methods includes determining, by one or more computers, spelling data that indicates the spelling of a word, providing the spelling data as input to a trained recurrent neural network, the trained recurrent neural network being trained to indicate characteristics of word pronunciations based at least on data indicating the spelling of words, receiving output indicating a stress pattern for pronunciation of the word generated by the trained recurrent neural network in response to providing the spelling data as input, using the output of the trained recurrent neural network to generate pronunciation data indicating the stress pattern for a pronunciation of the word, and providing, by the one or more computers, the pronunciation data to a text-to-speech system or an automatic speech recognition system.

3. 发明申请

US20170032792A1 SYSTEMS AND METHODS FOR DETERMINING MEANING OF CULTURAL GESTURES BASED ON VOICE DETECTION 审中-公开
标题翻译：基于语音检测确定文化语境意义的系统与方法
公开(公告)号：US20170032792A1
公开(公告)日：2017-02-02
申请号：US14813500
申请日：2015-07-30
申请人： ROVI GUIDES, INC.
发明人： Alejandro S. Pulido , Michael R. Nichols
IPC分类号： G10L17/26 , G06K9/00 , G06K9/66 , G10L25/78
CPC分类号： G06K9/00355 , G10L15/005 , G10L2015/027
摘要： In some embodiments, control circuitry may detect a voice communication from a human using voice detection circuitry during playback of a media asset being consumed by the user. Control circuitry may then identify an accent characteristic of the voice communication. Control circuitry may cross-reference the accent characteristic against listings of an accent database and then determine, based on the cross-referencing of the accent characteristic a country of origin of the human. Control circuitry may detect, using imaging circuitry, a gesture made by the human. Control circuitry may then cross-reference the gesture against listings of a gesture database associated with the country of origin and then determine based on the cross-referencing of the gesture, a meaning of the gesture in relation to the media asset.
摘要翻译：在一些实施例中，控制电路可以在用户正在消费的媒体资产的回放期间使用语音检测电路检测来自人的语音通信。然后，控制电路可以识别语音通信的重音特性。控制电路可以将口音特征与重音数据库的列表交叉引用，然后基于人类起源国的口音特征的交叉参考来确定。控制电路可以使用成像电路来检测由人造成的手势。控制电路然后可以将手势交叉引用与原始国家相关联的手势数据库的列表，然后基于手势的交叉参考来确定手势相对于媒体资产的含义。

4. 发明申请

US20160293184A1 METHOD AND COMPUTER SYSTEM FOR PERFORMING AUDIO SEARCH ON A SOCIAL NETWORKING PLATFORM 有权
标题翻译：用于在社交网络平台上执行音频搜索的方法和计算机系统
公开(公告)号：US20160293184A1
公开(公告)日：2016-10-06
申请号：US15176047
申请日：2016-06-07
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Lu LI , Jianxiong MA , Li LU
IPC分类号： G10L25/54 , G10L21/10 , G10L15/14
CPC分类号： G10L25/54 , G06F17/30026 , G10L15/14 , G10L21/10 , G10L2015/027 , G10L2015/088
摘要： Methods and computer systems for audio search on a social networking platform are disclosed. The method includes: while running a social networking application, receiving a first audio input from a user of the computer system, the first audio input including one or more search keywords; generating a first audio confusion network from the first audio input; determining whether the first audio confusion network matches at least one of one or more second audio confusion networks, wherein a respective second audio confusion network was generated from a corresponding second audio input associated with a Chat session of which the user is a participant; and identifying a second audio input corresponding to the at least one second audio confusion network that matches the first audio confusion network, wherein the identified second audio input includes the one or more search keywords that are included in the first audio input.
摘要翻译：公开了用于在社交网络平台上进行音频搜索的方法和计算机系统。该方法包括：在运行社交网络应用程序时，从计算机系统的用户接收第一音频输入，所述第一音频输入包括一个或多个搜索关键字; 从所述第一音频输入产生第一音频混淆网络; 确定所述第一音频混淆网络是否匹配一个或多个第二音频混淆网络中的至少一个，其中相应的第二音频混淆网络是从与所述用户是其参与者的聊天会话相关联的对应的第二音频输入生成的; 以及识别对应于与所述第一音频混淆网络匹配的所述至少一个第二音频混淆网络的第二音频输入，其中所识别的第二音频输入包括包括在所述第一音频输入中的所述一个或多个搜索关键字。

5. 发明申请

US20160275939A1 SPEECH RETRIEVAL METHOD, SPEECH RETRIEVAL APPARATUS, AND PROGRAM FOR SPEECH RETRIEVAL APPARATUS 有权
公开(公告)号：US20160275939A1
公开(公告)日：2016-09-22
申请号：US15167522
申请日：2016-05-27
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Gakuto Kurata , Tohru Nagano , Masafumi Nishimura
IPC分类号： G10L15/02 , G10L15/04 , G10L15/08 , G10L25/51
CPC分类号： G10L15/02 , G10L15/04 , G10L15/08 , G10L15/187 , G10L25/51 , G10L2015/025 , G10L2015/027 , G10L2015/088
摘要： A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.

6. 发明申请

US20160232892A1 METHOD AND APPARATUS OF EXPANDING SPEECH RECOGNITION DATABASE 审中-公开
标题翻译：扩展语音识别数据库的方法和设备
公开(公告)号：US20160232892A1
公开(公告)日：2016-08-11
申请号：US14991716
申请日：2016-01-08
申请人： Electronics and Telecommunications Research Institute
发明人： Yun-Joo KIM , Ju-Yeob KIM , Tae-Joong KIM
IPC分类号： G10L15/06 , G10L15/183 , G10L15/02 , G06F17/27 , G10L15/14
CPC分类号： G10L15/063 , G10L15/14 , G10L2015/025 , G10L2015/027 , G10L2015/0633 , G10L2015/0635
摘要： Disclosed herein are a method and an apparatus of expanding a speech recognition database used for speech recognition. The method of expanding a speech recognition database includes generating a pronunciation text from a corpus; confirming whether or not a non-registered word that is not registered in advance in a pronunciation dictionary among words included in the pronunciation text is present; generating lexical model information on the corresponding non-registered word with reference to a built-up acoustic model in the case in which the non-registered word is present as a confirmation result; and adding the generated lexical model information to a built-up lexical model. According to exemplary embodiments of the present invention, various speeches may be recognized in a stand-along speech recognizer in which an infrastructure is insufficient.
摘要翻译：这里公开了扩展用于语音识别的语音识别数据库的方法和装置。扩展语音识别数据库的方法包括从语料库生成发音文本; 确认在发音文本中包含的字之间是否存在在发音字典中未预先注册的未注册字; 在存在非注册字的情况下，参考建立的声学模型，在对应的非注册字上产生词汇模型信息作为确认结果; 并将生成的词汇模型信息添加到已建立的词汇模型中。根据本发明的示例性实施例，可以在基础设施不足的独立语音识别器中识别各种语音。

7. 发明授权

US09378736B2 Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus 有权
标题翻译：语音检索方法，语音检索装置，语音检索装置程序
公开(公告)号：US09378736B2
公开(公告)日：2016-06-28
申请号：US14692105
申请日：2015-04-21
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Gakuto Kurata , Tohru Nagano , Masafumi Nishimura
IPC分类号： G10L15/02 , G10L15/187 , G10L15/08
CPC分类号： G10L15/02 , G10L15/04 , G10L15/08 , G10L15/187 , G10L25/51 , G10L2015/025 , G10L2015/027 , G10L2015/088
摘要： A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.
摘要翻译：一种用于语音检索的方法包括获取由字符串指定的关键字，以及音素串或音节串，通过将作为语音识别的识别结果的字符串与作为识别单元执行的字比较来检测一个或多个重合片段对于要检索的语音数据和关键词的字符串，通过使用该关键字的音素字符串或音节字符串来计算一个或多个片段中的每一个片段的评估值，以评估被识别的音素字符串或音节字符串在检测到的一个或多个段中的每一个中，并且是以音素或音节作为对于语音数据执行的识别单元的音素语音识别的识别结果，并且输出其中所计算的评估值超过预定阈值的段。

8. 发明授权

US09373328B2 Speech retrieval method, speech retrieval apparatus, and program for speech retrieval apparatus 有权
公开(公告)号：US09373328B2
公开(公告)日：2016-06-21
申请号：US14745912
申请日：2015-06-22
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Gakuto Kurata , Tohru Nagano , Masafumi Nishimura
IPC分类号： G10L15/02 , G10L15/187 , G10L15/08
CPC分类号： G10L15/02 , G10L15/04 , G10L15/08 , G10L15/187 , G10L25/51 , G10L2015/025 , G10L2015/027 , G10L2015/088
摘要： A method for speech retrieval includes acquiring a keyword designated by a character string, and a phoneme string or a syllable string, detecting one or more coinciding segments by comparing a character string that is a recognition result of word speech recognition with words as recognition units performed for speech data to be retrieved and the character string of the keyword, calculating an evaluation value of each of the one or more segments by using the phoneme string or the syllable string of the keyword to evaluate a phoneme string or a syllable string that is recognized in each of the detected one or more segments and that is a recognition result of phoneme speech recognition with phonemes or syllables as recognition units performed for the speech data, and outputting a segment in which the calculated evaluation value exceeds a predetermined threshold.

9. 发明申请

US20160118039A1 SOUND SAMPLE VERIFICATION FOR GENERATING SOUND DETECTION MODEL 有权
标题翻译：用于生成声音检测模型的声音样本验证
公开(公告)号：US20160118039A1
公开(公告)日：2016-04-28
申请号：US14682009
申请日：2015-04-08
申请人： QUALCOMM Incorporated
发明人： Sunkuk Moon , Minho Jin , Haiying Xia , Hesu Huang , Warren Frederick Dale
IPC分类号： G10L15/02 , G10L15/08 , G10L15/22
CPC分类号： G10L15/02 , G10L15/063 , G10L15/08 , G10L15/22 , G10L2015/022 , G10L2015/025 , G10L2015/027
摘要： A method for verifying at least one sound sample to be used in generating a sound detection model in an electronic device includes receiving a first sound sample; extracting a first acoustic feature from the first sound sample; receiving a second sound sample; extracting a second acoustic feature from the second sound sample; and determining whether the second acoustic feature is similar to the first acoustic feature.
摘要翻译：一种用于验证用于在电子设备中生成声音检测模型的至少一个声音样本的方法包括：接收第一声音样本; 从所述第一声音样本中提取第一声学特征; 接收第二个声音样本; 从所述第二声音样本中提取第二声学特征; 以及确定所述第二声学特征是否类似于所述第一声学特征。

10. 发明授权

US09082404B2 Recognizing device, computer-readable recording medium, recognizing method, generating device, and generating method 有权
标题翻译：识别装置，计算机可读记录介质，识别方法，生成装置和生成方法
公开(公告)号：US09082404B2
公开(公告)日：2015-07-14
申请号：US13586533
申请日：2012-08-15
申请人： Shouji Harada
发明人： Shouji Harada
IPC分类号： G10L15/00 , G10L21/00 , G10L25/00 , G10L15/04 , G10L15/26 , G10L15/06 , G10L17/00 , G10L15/28 , G06F17/28 , G06F17/27 , G06F17/21 , G10L15/19 , G10L15/10 , G10L15/02
CPC分类号： G10L15/19 , G10L15/10 , G10L2015/027
摘要： A recognizing device includes a memory and a processor coupled to the memory. The memory stores words included in a text and positional information indicating a position of the words in the text. The processor executes a process including comparing an input voice signal with reading information of a character string that connects a plurality of words stored in the memory to calculate a similarity; calculating a connection score indicating a proximity between the plurality of connected words based on positional information of the words stored in the memory; and determining a character string corresponding to the voice signal based on the similarity and the connection score.
摘要翻译：识别装置包括存储器和耦合到存储器的处理器。存储器存储包括在文本中的单词和表示文本中单词的位置的位置信息。处理器执行处理，其包括将输入语音信号与连接存储在存储器中的多个字的字符串的读取信息进行比较，以计算相似度; 基于存储在存储器中的字的位置信息计算指示多个连接字之间的接近度的连接得分; 以及基于所述相似度和所述连接得分来确定与所述语音信号相对应的字符串。

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