利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.013 秒)

    DYNAMICALLY ADDING PERSONALIZATION FEATURES TO LANGUAGE MODELS FOR VOICE SEARCH
    1.
    发明申请
    DYNAMICALLY ADDING PERSONALIZATION FEATURES TO LANGUAGE MODELS FOR VOICE SEARCH 有权
    动态添加个性化功能语言模型语音搜索

    公开(公告)号：US20120316877A1

    公开(公告)日：2012-12-13

    申请号：US13158453

    申请日：2011-06-12

    申请人： Geoffrey Zweig ,  Shuangyu Chang

    发明人： Geoffrey Zweig ,  Shuangyu Chang

    IPC分类号： G10L15/04

    CPC分类号： G10L15/197 ,  G10L15/07

    摘要： A dynamic exponential, feature-based, language model is continually adjusted per utterance by a user, based on the user's usage history. This adjustment of the model is done incrementally per user, over a large number of users, each with a unique history. The user history can include previously recognized utterances, text queries, and other user inputs. The history data for a user is processed to derive features. These features are then added into the language model dynamically for that user.

    摘要翻译： 基于用户的使用历史，用户每个话语不断调整动态指数，基于特征的语言模型。 模型的这种调整是每个用户逐步完成的，在大量用户中，每个用户都有独特的历史记录。 用户历史可以包括先前识别的话语，文本查询和其他用户输入。 处理用户的历史数据以导出特征。 然后将这些功能动态地添加到该用户的语言模型中。

    Dynamically adding personalization features to language models for voice search
    2.
    发明授权
    Dynamically adding personalization features to language models for voice search 有权
    动态地将个性化功能添加到语音搜索的语言模型中

    公开(公告)号：US08938391B2

    公开(公告)日：2015-01-20

    申请号：US13158453

    申请日：2011-06-12

    申请人： Geoffrey Zweig ,  Shuangyu Chang

    发明人： Geoffrey Zweig ,  Shuangyu Chang

    IPC分类号： G10L15/04

    CPC分类号： G10L15/197 ,  G10L15/07

    摘要： A dynamic exponential, feature-based, language model is continually adjusted per utterance by a user, based on the user's usage history. This adjustment of the model is done incrementally per user, over a large number of users, each with a unique history. The user history can include previously recognized utterances, text queries, and other user inputs. The history data for a user is processed to derive features. These features are then added into the language model dynamically for that user.

    摘要翻译： 基于用户的使用历史，用户每个话语不断调整动态指数，基于特征的语言模型。 模型的这种调整是每个用户逐步完成的，在大量用户中，每个用户都有独特的历史记录。 用户历史可以包括先前识别的话语，文本查询和其他用户输入。 处理用户的历史数据以导出特征。 然后将这些功能动态地添加到该用户的语言模型中。

    Speech recognition accuracy with multi-confidence thresholds
    4.
    发明授权
    Speech recognition accuracy with multi-confidence thresholds 有权
    具有多重置信度阈值的语音识别精度

    公开(公告)号：US07657433B1

    公开(公告)日：2010-02-02

    申请号：US11530212

    申请日：2006-09-08

    申请人： Shuangyu Chang

    发明人： Shuangyu Chang

    IPC分类号： G10L15/04

    CPC分类号： G10L15/08

    摘要： A speech recognition system uses multiple confidence thresholds to improve the quality of speech recognition results. The choice of which confidence threshold to use for a particular utterance may be based on one or more features relating to the utterance. In one particular implementation, the speech recognition system includes a speech recognition engine that provides speech recognition results and a confidence score for an input utterance. The system also includes a threshold selection component that determines, based on the received input utterance, a threshold value corresponding to the input utterance. The system further includes a threshold component that accepts the recognition results based on a comparison of the confidence score to the threshold value.

    摘要翻译： 语音识别系统使用多个置信阈值来提高语音识别结果的质量。 用于特定话语的置信阈值的选择可以基于与话语相关的一个或多个特征。 在一个特定实施方式中，语音识别系统包括语音识别引擎，其为输入话语提供语音识别结果和置信度分数。 该系统还包括阈值选择部件，该阈值选择部件基于接收到的输入话语来确定与输入的话语对应的阈值。 该系统还包括基于置信度分数与阈值的比较来接受识别结果的阈值分量。

    RECOGNITION USING RE-RECOGNITION AND STATISTICAL CLASSIFICATION
    6.
    发明申请
    RECOGNITION USING RE-RECOGNITION AND STATISTICAL CLASSIFICATION 有权
    使用重新识别和统计分类的识别

    公开(公告)号：US20100312546A1

    公开(公告)日：2010-12-09

    申请号：US12477918

    申请日：2009-06-04

    申请人： Shuangyu Chang ,  Michael Levit ,  Bruce Buntschuh

    发明人： Shuangyu Chang ,  Michael Levit ,  Bruce Buntschuh

    IPC分类号： G10L15/18

    CPC分类号： G06N99/005 ,  G10L15/08 ,  G10L15/19 ,  G10L15/32 ,  G10L2015/228

    摘要： Architecture that employs an overall grammar as a set of context-specific grammars for recognition of an input, each responsible for a specific context, such as subtask category, geographic region, etc. The grammars together cover the entire domain. Moreover, multiple recognitions can be run in parallel against the same input, where each recognition uses one or more of the context-specific grammars. The multiple intermediate recognition results from the different recognizer-grammars are reconciled by running re-recognition using a dynamically composed grammar based on the multiple recognition results and potentially other domain knowledge, or selecting the winner using a statistical classifier operating on classification features extracted from the multiple recognition results and other domain knowledge.

    摘要翻译： 使用整体语法作为一组上下文特定语法的体系结构，用于识别输入，每个语言负责特定上下文，例如子任务类别，地理区域等。语法一起涵盖整个域。 此外，可以针对相同的输入并行运行多个识别，其中每个识别使用一个或多个上下文特定语法。 通过使用基于多个识别结果和潜在的其他领域知识的动态组合语法运行重新识别来协调来自不同识别器语法的多个中间识别结果，或者使用对从分类特征提取的分类特征进行运算的统计分类器来选择胜者 多重识别结果等领域知识。

    SEQUENTIAL SPEECH RECOGNITION WITH TWO UNEQUAL ASR SYSTEMS
    8.
    发明申请
    SEQUENTIAL SPEECH RECOGNITION WITH TWO UNEQUAL ASR SYSTEMS 有权
    具有两个非正常ASR系统的顺序语音识别

    公开(公告)号：US20100082343A1

    公开(公告)日：2010-04-01

    申请号：US12240143

    申请日：2008-09-29

    申请人： Michael Levit ,  Shuangyu Chang ,  Bruce Melvin Buntschuh

    发明人： Michael Levit ,  Shuangyu Chang ,  Bruce Melvin Buntschuh

    IPC分类号： G10L15/18

    CPC分类号： G10L15/32 ,  G10L2015/0631

    摘要： Sequential speech recognition using two unequal automatic speech recognition (ASR) systems may be provided. The system may provide two sets of vocabulary data. A determination may be made as to whether entries in one set of vocabulary data are likely to be confused with entries in the other set of vocabulary data. If confusion is likely, a decoy entry from one set of the vocabulary data may be placed in the other set of vocabulary data to ensure more efficient and accurate speech recognition processing may take place.

    摘要翻译： 可以提供使用两个不等的自动语音识别（ASR）系统的顺序语音识别。 系统可以提供两组词汇数据。 可以确定一组词汇数据中的条目是否可能与另一组词汇数据中的条目混淆。 如果混淆很可能，则一组词汇数据中的诱饵条目可以被放置在另一组词汇数据中，以确保可能发生更有效和准确的语音识别处理。

    Recognition using re-recognition and statistical classification
    9.
    发明授权
    Recognition using re-recognition and statistical classification 有权
    识别使用重新识别和统计分类

    公开(公告)号：US08930179B2

    公开(公告)日：2015-01-06

    申请号：US12477918

    申请日：2009-06-04

    申请人： Shuangyu Chang ,  Michael Levit ,  Bruce Buntschuh

    发明人： Shuangyu Chang ,  Michael Levit ,  Bruce Buntschuh

    IPC分类号： G06F17/27

    CPC分类号： G06N99/005 ,  G10L15/08 ,  G10L15/19 ,  G10L15/32 ,  G10L2015/228

    摘要： Architecture that employs an overall grammar as a set of context-specific grammars for recognition of an input, each responsible for a specific context, such as subtask category, geographic region, etc. The grammars together cover the entire domain. Moreover, multiple recognitions can be run in parallel against the same input, where each recognition uses one or more of the context-specific grammars. The multiple intermediate recognition results from the different recognizer-grammars are reconciled by running re-recognition using a dynamically composed grammar based on the multiple recognition results and potentially other domain knowledge, or selecting the winner using a statistical classifier operating on classification features extracted from the multiple recognition results and other domain knowledge.

    摘要翻译： 使用整体语法作为一组上下文特定语法的体系结构，用于识别输入，每个语言负责特定上下文，例如子任务类别，地理区域等。语法一起涵盖整个域。 此外，可以针对相同的输入并行运行多个识别，其中每个识别使用一个或多个上下文特定语法。 通过使用基于多个识别结果和潜在的其他领域知识的动态组合语法运行重新识别来协调来自不同识别器语法的多个中间识别结果，或者使用对从分类特征提取的分类特征进行运算的统计分类器来选择胜者 多重识别结果等领域知识。