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. 发明授权

US08060494B2 Indexing and searching audio using text indexers 有权
标题翻译：使用文本索引器索引和搜索音频
公开(公告)号：US08060494B2
公开(公告)日：2011-11-15
申请号：US11952817
申请日：2007-12-07
申请人： Frank T. B. Seide , Peng Yu , Albert Joseph Kishan Thambiratnam
发明人： Frank T. B. Seide , Peng Yu , Albert Joseph Kishan Thambiratnam
IPC分类号： G06F17/00
CPC分类号： G06F17/30746 , G06F17/30778
摘要： A full-text lattice indexing and searching system and method for indexing word lattices using a text indexer to enable enhance searching of audio content. The system and method utilize a Time-Anchored Lattice Expansion (TALE) method that represents word lattices such that they can be indexed with existing text indexers with little or no modification. Embodiments of system and method include an indexing module for generating and indexing word lattices based on audio content and a searching module for allowing searching of a full-text index containing indexed word lattices. The indexing module includes a custom IFilter and a custom Wordbreaker. Embodiments of the searching module include an ExpandQuery function for decorating an input query and a custom Stemmer. Embodiments of the searching module also include a GenerateSnippets module that extracts information from the indexed word lattices to enable the creation of clickable snippets.
摘要翻译：一种全文格式索引和搜索系统和方法，用于使用文本索引器索引字格，以增强对音频内容的搜索。该系统和方法利用代表字格的时间锚定格子扩展（TALE）方法，使得它们可以用很少或没有修改的现有文本索引器进行索引。系统和方法的实施例包括用于基于音频内容生成和索引字格的索引模块和用于允许搜索包含索引的字格的全文索引的搜索模块。索引模块包括一个自定义的IFilter和一个自定义的Wordbreaker。搜索模块的实施例包括用于装饰输入查询和定制Stemmer的ExpandQuery函数。搜索模块的实施例还包括GenerateSnippets模块，该模块从索引的字格架提取信息，以创建可点击的片段。

2. 发明申请

US20100268534A1 TRANSCRIPTION, ARCHIVING AND THREADING OF VOICE COMMUNICATIONS 审中-公开
标题翻译：语音通信的转录，存档和打包
公开(公告)号：US20100268534A1
公开(公告)日：2010-10-21
申请号：US12425841
申请日：2009-04-17
申请人： ALBERT JOSEPH KISHAN THAMBIRATNAM , FRANK TORSTEN BERND SEIDE , PENG YU , ROY GEOFFREY WALLACE
发明人： ALBERT JOSEPH KISHAN THAMBIRATNAM , FRANK TORSTEN BERND SEIDE , PENG YU , ROY GEOFFREY WALLACE
IPC分类号： G10L15/26 , G10L17/00
CPC分类号： G10L15/07 , G10L15/26 , G10L15/30
摘要： Described is a technology that provides highly accurate speech-recognized text transcripts of conversations, particularly telephone or meeting conversations. Speech is received for recognition when it is at a high quality and separate for each user, that is, independent of any transmission. Moreover, because the speech is received separately, a personalized recognition model adapted to each user's voice and vocabulary may be used. The separately recognized text is then merged into a transcript of the communication. The transcript may be labeled with the identity of each user that spoke the corresponding speech. The output of the transcript may be dynamic as the conversation takes place, or may occur later, such as contingent upon each user agreeing to release his or her text. The transcript may be incorporated into the text or data of another program, such as to insert it as a thread in a larger email conversation or the like.
摘要翻译：描述了一种技术，可以提供高度准确的语音识别的会话文本，特别是电话或会议对话。接收到用于识别的语音，当其处于高质量并且针对每个用户分离时，即独立于任何传输。此外，由于单独接收语音，因此可以使用适合于每个用户的语音和词汇的个性化识别模型。然后将单独识别的文本合并到通信的抄本中。誊本可以标注每个使用相应语音的用户的身份。誊本的输出可能会随着会话的发生而发生，也可能发生在以后，例如随着每个用户同意发布他或她的文本。脚本可以并入另一程序的文本或数据中，例如将其作为线程插入较大的电子邮件会话等中。

3. 发明授权

US09483557B2 Keyword generation for media content 有权
标题翻译：媒体内容的关键字生成
公开(公告)号：US09483557B2
公开(公告)日：2016-11-01
申请号：US13040640
申请日：2011-03-04
申请人： Albert Joseph Kishan Thambiratnam , Sha Meng , Gang Li , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Sha Meng , Gang Li , Frank Torsten Bernd Seide
IPC分类号： G06F17/30
CPC分类号： G06F17/30796 , G06F17/30864
摘要： In various embodiments, a transcript that represents a media file is created. Keyword candidates that may represent topics and/or content associated with the media content are then be extracted from the transcript. Furthermore, a keyword set may be generated for the media content utilizing a mutual information criteria. In other embodiments, one or more queries may be generated based at least in part on the transcript, and a plurality of web documents may be retrieved based at least in part on the one or more queries. Additional keyword candidates may be extracted from each web document and then ranked. A subset of the keyword candidates may then be selected to form a keyword set associated with the media content.
摘要翻译：在各种实施例中，创建表示媒体文件的抄本。然后可以从成绩单中提取可能表示与媒体内容相关联的主题和/或内容的关键字候选。此外，可以利用互信息标准为媒体内容生成关键字集合。在其他实施例中，可以至少部分地基于抄本生成一个或多个查询，并且可以至少部分地基于一个或多个查询来检索多个web文档。可以从每个web文档中提取附加的关键字候选，然后排序。然后可以选择关键字候选的子集以形成与媒体内容相关联的关键字集合。

4. 发明申请

US20120221330A1 LEVERAGING SPEECH RECOGNIZER FEEDBACK FOR VOICE ACTIVITY DETECTION 有权
标题翻译：引导语音识别器反馈进行语音活动检测
公开(公告)号：US20120221330A1
公开(公告)日：2012-08-30
申请号：US13035044
申请日：2011-02-25
申请人： Albert Joseph Kishan Thambiratnam , Weiwu Zhu , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Weiwu Zhu , Frank Torsten Bernd Seide
IPC分类号： G10L15/26 , G10L15/00
CPC分类号： G10L25/84 , G10L15/04 , G10L15/26 , G10L25/45
摘要： A voice activity detection (VAD) module analyzes a media file, such as an audio file or a video file, to determine whether one or more frames of the media file include speech. A speech recognizer generates feedback relating to an accuracy of the VAD determination. The VAD module leverages the feedback to improve subsequent VAD determinations. The VAD module also utilizes a look-ahead window associated with the media file to adjust estimated probabilities or VAD decisions for previously processed frames.
摘要翻译：语音活动检测（VAD）模块分析诸如音频文件或视频文件的媒体文件，以确定媒体文件的一个或多个帧是否包含语音。语音识别器产生与VAD确定的精度有关的反馈。 VAD模块利用反馈来改进随后的VAD确定。 VAD模块还利用与媒体文件相关联的预览窗口来调整对先前处理的帧的估计概率或VAD决定。

5. 发明申请

US20130191126A1 Subword-Based Multi-Level Pronunciation Adaptation for Recognizing Accented Speech 有权
标题翻译：基于字的多层次发音适应识别口音
公开(公告)号：US20130191126A1
公开(公告)日：2013-07-25
申请号：US13355215
申请日：2012-01-20
申请人： Albert Joseph Kishan Thambiratnam , Timo Pascal Mertens , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Timo Pascal Mertens , Frank Torsten Bernd Seide
IPC分类号： G10L15/06
CPC分类号： G10L15/187 , G10L15/06
摘要： Techniques are described for training a speech recognition model for accented speech. A subword parse table is employed that models mispronunciations at multiple subword levels, such as the syllable, position-specific cluster, and/or phone levels. Mispronunciation probability data is then generated at each level based on inputted training data, such as phone-level annotated transcripts of accented speech. Data from different levels of the subword parse table may then be combined to determine the accented speech model. Mispronunciation probability data at each subword level is based at least in part on context at that level. In some embodiments, phone-level annotated transcripts are generated using a semi-supervised method.
摘要翻译：描述了用于训练重音语音的语音识别模型的技术。使用子字解析表来对多个子词级别（例如音节，位置特定的群集和/或电话层级）进行误导。然后基于输入的训练数据（例如重音语音的电话级注释誊本）在每个级别生成分秒传播概率数据。然后可以组合来自子词解析表的不同级别的数据以确定重音语音模型。每个子词级别的通配概率数据至少部分地基于该级别的上下文。在一些实施例中，使用半监督方法生成电话级注释的记录。

6. 发明申请

US20090150337A1 INDEXING AND SEARCHING AUDIO USING TEXT INDEXERS 有权
标题翻译：使用文本索引进行索引和搜索音频
公开(公告)号：US20090150337A1
公开(公告)日：2009-06-11
申请号：US11952817
申请日：2007-12-07
申请人： Frank T.B. Seide , Peng Yu , Albert Joseph Kishan Thambiratnam
发明人： Frank T.B. Seide , Peng Yu , Albert Joseph Kishan Thambiratnam
IPC分类号： G06F17/30
CPC分类号： G06F17/30746 , G06F17/30778
摘要： A full-text lattice indexing and searching system and method for indexing word lattices using a text indexer to enable enhance searching of audio content. The system and method utilize a Time-Anchored Lattice Expansion (TALE) method that represents word lattices such that they can be indexed with existing text indexers with little or no modification. Embodiments of system and method include an indexing module for generating and indexing word lattices based on audio content and a searching module for allowing searching of a full-text index containing indexed word lattices. The indexing module includes a custom IFilter and a custom Wordbreaker. Embodiments of the searching module include an ExpandQuery function for decorating an input query and a custom Stemmer. Embodiments of the searching module also include a GenerateSnippets module that extracts information from the indexed word lattices to enable the creation of clickable snippets.
摘要翻译：一种全文格式索引和搜索系统和方法，用于使用文本索引器索引字格，以增强对音频内容的搜索。该系统和方法利用代表字格的时间锚定格子扩展（TALE）方法，使得它们可以用很少或没有修改的现有文本索引器进行索引。系统和方法的实施例包括用于基于音频内容生成和索引字格的索引模块和用于允许搜索包含索引的字格的全文索引的搜索模块。索引模块包括一个自定义的IFilter和一个自定义的Wordbreaker。搜索模块的实施例包括用于装饰输入查询和定制Stemmer的ExpandQuery函数。搜索模块的实施例还包括GenerateSnippets模块，该模块从索引的字格架提取信息，以创建可点击的片段。

7. 发明授权

US08650029B2 Leveraging speech recognizer feedback for voice activity detection 有权
标题翻译：利用语音识别器反馈进行语音活动检测
公开(公告)号：US08650029B2
公开(公告)日：2014-02-11
申请号：US13035044
申请日：2011-02-25
申请人： Albert Joseph Kishan Thambiratnam , Weiwu Zhu , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Weiwu Zhu , Frank Torsten Bernd Seide
IPC分类号： G10L15/00
CPC分类号： G10L25/84 , G10L15/04 , G10L15/26 , G10L25/45
摘要： A voice activity detection (VAD) module analyzes a media file, such as an audio file or a video file, to determine whether one or more frames of the media file include speech. A speech recognizer generates feedback relating to an accuracy of the VAD determination. The VAD module leverages the feedback to improve subsequent VAD determinations. The VAD module also utilizes a look-ahead window associated with the media file to adjust estimated probabilities or VAD decisions for previously processed frames.
摘要翻译：语音活动检测（VAD）模块分析诸如音频文件或视频文件的媒体文件，以确定媒体文件的一个或多个帧是否包含语音。语音识别器产生与VAD确定的精度有关的反馈。 VAD模块利用反馈来改进随后的VAD确定。 VAD模块还利用与媒体文件相关联的预览窗口来调整对先前处理的帧的估计概率或VAD决定。

8. 发明申请

US20120226696A1 Keyword Generation for Media Content 有权
标题翻译：媒体内容的关键字生成
公开(公告)号：US20120226696A1
公开(公告)日：2012-09-06
申请号：US13040640
申请日：2011-03-04
申请人： Albert Joseph Kishan Thambiratnam , Sha Meng , Gang Li , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Sha Meng , Gang Li , Frank Torsten Bernd Seide
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30796 , G06F17/30864
摘要： In various embodiments, a transcript that represents a media file is created. Keyword candidates that may represent topics and/or content associated with the media content are then be extracted from the transcript. Furthermore, a keyword set may be generated for the media content utilizing a mutual information criteria. In other embodiments, one or more queries may be generated based at least in part on the transcript, and a plurality of web documents may be retrieved based at least in part on the one or more queries. Additional keyword candidates may be extracted from each web document and then ranked. A subset of the keyword candidates may then be selected to form a keyword set associated with the media content.
摘要翻译：在各种实施例中，创建表示媒体文件的抄本。然后可以从成绩单中提取可能表示与媒体内容相关联的主题和/或内容的关键字候选。此外，可以利用互信息标准为媒体内容生成关键字集合。在其他实施例中，可以至少部分地基于抄本生成一个或多个查询，并且可以至少部分地基于一个或多个查询来检索多个web文档。可以从每个web文档中提取附加的关键字候选，然后排序。然后可以选择关键字候选的子集以形成与媒体内容相关联的关键字集合。

9. 发明授权

US08825481B2 Subword-based multi-level pronunciation adaptation for recognizing accented speech 有权
标题翻译：用于识别重音语音的基于字的多级发音适应
公开(公告)号：US08825481B2
公开(公告)日：2014-09-02
申请号：US13355215
申请日：2012-01-20
申请人： Albert Joseph Kishan Thambiratnam , Timo Pascal Mertens , Frank Torsten Bernd Seide
发明人： Albert Joseph Kishan Thambiratnam , Timo Pascal Mertens , Frank Torsten Bernd Seide
IPC分类号： G10L15/00 , G10L15/06
CPC分类号： G10L15/187 , G10L15/06
摘要： Techniques are described for training a speech recognition model for accented speech. A subword parse table is employed that models mispronunciations at multiple subword levels, such as the syllable, position-specific cluster, and/or phone levels. Mispronunciation probability data is then generated at each level based on inputted training data, such as phone-level annotated transcripts of accented speech. Data from different levels of the subword parse table may then be combined to determine the accented speech model. Mispronunciation probability data at each subword level is based at least in part on context at that level. In some embodiments, phone-level annotated transcripts are generated using a semi-supervised method.
摘要翻译：描述了用于训练重音语音的语音识别模型的技术。使用子字解析表来对多个子词级别（例如音节，位置特定的群集和/或电话层级）进行误导。然后基于输入的训练数据（例如重音语音的电话级注释誊本），在每个级别生成分数概率数据。然后可以组合来自子词解析表的不同级别的数据以确定重音语音模型。每个子词级别的通配概率数据至少部分地基于该级别的上下文。在一些实施例中，使用半监督方法生成电话级注释的记录。

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