利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

18 条记录 (耗时 0.022 秒)

    Speech recognition using multiple language models
    2.
    发明授权
    Speech recognition using multiple language models 有权
    多语言模型的语音识别

    公开(公告)号：US08972260B2

    公开(公告)日：2015-03-03

    申请号：US13450861

    申请日：2012-04-19

    申请人： Fuliang Weng ,  Zhe Feng ,  Kui Xu ,  Lin Zhao

    发明人： Fuliang Weng ,  Zhe Feng ,  Kui Xu ,  Lin Zhao

    IPC分类号： G10L15/00 ,  G10L15/32 ,  G10L15/06 ,  G10L15/18 ,  G10L15/193 ,  G10L15/197 ,  G10L15/30

    CPC分类号： G10L15/32 ,  G10L15/063 ,  G10L15/18 ,  G10L15/193 ,  G10L15/197 ,  G10L15/30

    摘要： In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.

    摘要翻译： 根据一个实施例，一种生成用于语音识别的语言模型的方法包括：识别与语音相对应的训练数据中的多个话语，产生多个话语中的每个发声的频率计数，从多个话语中产生高频多个话语 所述多个话音具有超过预定频率阈值的频率，从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语，使用所述高频率生成基于语法的语言模型 多个话语作为训练数据，并且使用低频多个话语生成统计语言模型作为训练数据。

    SPEECH RECOGNITION USING MULTIPLE LANGUAGE MODELS
    3.
    发明申请
    SPEECH RECOGNITION USING MULTIPLE LANGUAGE MODELS 有权
    使用多种语言模型进行语音识别

    公开(公告)号：US20120271631A1

    公开(公告)日：2012-10-25

    申请号：US13450861

    申请日：2012-04-19

    申请人： Fuliang Weng ,  Zhe Feng ,  Kui Xu ,  Lin Zhao

    发明人： Fuliang Weng ,  Zhe Feng ,  Kui Xu ,  Lin Zhao

    IPC分类号： G10L15/06

    CPC分类号： G10L15/32 ,  G10L15/063 ,  G10L15/18 ,  G10L15/193 ,  G10L15/197 ,  G10L15/30

    摘要： In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data.

    摘要翻译： 根据一个实施例，一种生成用于语音识别的语言模型的方法包括：识别与语音相对应的训练数据中的多个话语，产生多个话语中的每个发声的频率计数，从多个话语中产生高频多个话语 所述多个话音具有超过预定频率阈值的频率，从具有低于所述预定频率阈值的频率的所述多个话语中产生低频多个话语，使用所述高频率生成基于语法的语言模型 多个话语作为训练数据，并且使用低频多个话语生成统计语言模型作为训练数据。

    System and Method for Interacting with Live Agents in an Automated Call Center
    5.
    发明申请
    System and Method for Interacting with Live Agents in an Automated Call Center 有权
    在自动呼叫中心与实时代理交互的系统和方法

    公开(公告)号：US20100124325A1

    公开(公告)日：2010-05-20

    申请号：US12274258

    申请日：2008-11-19

    申请人： Fuliang Weng ,  Baoshi Yan ,  Zhongnan Shen ,  Zhe Feng ,  Kui Xu ,  Katrina Li

    发明人： Fuliang Weng ,  Baoshi Yan ,  Zhongnan Shen ,  Zhe Feng ,  Kui Xu ,  Katrina Li

    IPC分类号： H04M3/00 ,  G10L15/04

    CPC分类号： H04M3/5166 ,  G10L15/22 ,  H04M2201/40

    摘要： Embodiments of an interface system that enables a call center agent to access and intervene in an interaction between an automated call center system and a caller whenever necessary for complex application tasks is described. The system includes a user interface that presents the agent with one or more categories of information, including the conversation flow, obtained semantic information, the recognized utterances, and access to the utterance waveforms. This information is cross-linked and attached with a confidence level for better access and navigation within the dialog system for the generation of appropriate responses to the caller.

    摘要翻译： 描述了使得呼叫中心代理能够访问并介入自动呼叫中心系统和呼叫者之间的交互的接口系统的实施例，以便在需要复杂的应用任务时。 该系统包括用户界面，其向代理呈现一个或多个类别的信息，包括会话流，获得的语义信息，识别的话语和对话音波形的访问。 该信息是交叉链接的，并附有置信水平，以便在对话系统内更好地访问和导航以产生对呼叫者的适当响应。

    Method and system for learning ontological relations from documents
    8.
    发明授权
    Method and system for learning ontological relations from documents 有权
    从文件学习本体论关系的方法和系统

    公开(公告)号：US07630981B2

    公开(公告)日：2009-12-08

    申请号：US11645386

    申请日：2006-12-26

    申请人： Kui Xu ,  Fuliang Weng

    发明人： Kui Xu ,  Fuliang Weng

    IPC分类号： G06F17/30

    CPC分类号： G10L15/1815 ,  G10L15/183 ,  Y10S707/99933 ,  Y10S707/99936 ,  Y10S707/99942

    摘要： Embodiments of an ontological determination method for use in natural language processing applications are described. In one embodiment, shallow lexico-syntactic patterns are applied to identify relations by extracting term features to distinguish relation terms from non-relation terms, identifying coordinate relations for every adjacent terms; identifying short-distance ontological (e.g., hypernym or part-whole relations) for other adjacent terms based on term features and lexico-syntactic patterns; and then inferring long-distance hypernym and part-whole relations based on the identified coordinate relations and the short-distance relations.

    摘要翻译： 描述了在自然语言处理应用中使用的本体确定方法的实施例。 在一个实施例中，应用浅层词典模式以通过提取术语特征来识别关系，以将关系项与非关系术语区分开来，识别每个相邻术语的坐标关系; 基于术语特征和词典语法模式识别其他相邻术语的短距离本体论（例如，超音阶或部分整体关系）; 然后根据确定的协调关系和短距离关系推断出长距离超高和部分整体关系。

    Dialogue management using scripts and combined confidence scores
    9.
    发明授权
    Dialogue management using scripts and combined confidence scores 有权
    对话管理使用脚本和组合的置信分数

    公开(公告)号：US07904297B2

    公开(公告)日：2011-03-08

    申请号：US11298765

    申请日：2005-12-08

    申请人： Danilo Mirkovic ,  Lawrence Cavedon ,  Matthew Purver ,  Florin Ratiu ,  Tobias Scheideck ,  Fuliang Weng ,  Qi Zhang ,  Kui Xu

    发明人： Danilo Mirkovic ,  Lawrence Cavedon ,  Matthew Purver ,  Florin Ratiu ,  Tobias Scheideck ,  Fuliang Weng ,  Qi Zhang ,  Kui Xu

    IPC分类号： G10L15/00 ,  G10L15/08

    CPC分类号： G06F17/28 ,  G10L2015/228

    摘要： Representation-neutral dialogue systems and methods (“RNDS”) are described that include multi-application, multi-device spoken-language dialogue systems based on the information-state update approach. The RNDS includes representation-neutral core components of a dialogue system that provide scripted domain-specific extensions to routines such as dialogue move modeling and reference resolution, easy substitution of specific semantic representations and associated routines, and clean interfaces to external components for language-understanding (i.e., speech-recognition and parsing) and language-generation, and to domain-specific knowledge sources. The RNDS also resolves multi-device dialogue by evaluating and selecting among candidate dialogue moves based on features at multiple levels. Multiple sources of information are combined, multiple speech recognition and parsing hypotheses tested, and multiple device and moves considered to choose the highest scoring hypothesis overall. Confirmation and clarification behavior can be governed by the overall score.

    摘要翻译： 描述了中立的对话系统和方法（“RNDS”），其包括基于信息状态更新方法的多应用，多设备语言对话系统。 RNDS包括对话系统的代表性中立的核心组件，其提供脚本特定的例程扩展，例如对话移动建模和参考解析，容易地替换特定的语义表示和相关联的例程，以及将外部组件的界面清理为语言理解 （即语音识别和解析）和语言生成以及针对领域的知识来源。 RNDS还通过基于多层次的特征评估和选择候选对话移动来解决多设备对话。 多个信息来源相结合，多个语音识别和解析假设被测试，多个设备和移动被认为是选择最高的得分假设。 确认和澄清行为可以由总体评分来决定。

    Method and system for learning ontological relations from documents
    10.
    发明申请
    Method and system for learning ontological relations from documents 有权
    从文件学习本体论关系的方法和系统

    公开(公告)号：US20080154578A1

    公开(公告)日：2008-06-26

    申请号：US11645386

    申请日：2006-12-26

    申请人： Kui Xu ,  Fuliang Weng

    发明人： Kui Xu ,  Fuliang Weng

    IPC分类号： G10L13/08

    CPC分类号： G10L15/1815 ,  G10L15/183 ,  Y10S707/99933 ,  Y10S707/99936 ,  Y10S707/99942

    摘要： Embodiments of an ontological determination method for use in natural language processing applications are described. In one embodiment, shallow lexico-syntactic patterns are applied to identify relations by extracting term features to distinguish relation terms from non-relation terms, identifying coordinate relations for every adjacent terms; identifying short-distance ontological (e.g., hypernym or part-whole relations) for other adjacent terms based on term features and lexico-syntactic patterns; and then inferring long-distance hypernym and part-whole relations based on the identified coordinate relations and the short-distance relations.

    摘要翻译： 描述了在自然语言处理应用中使用的本体确定方法的实施例。 在一个实施例中，应用浅层词典模式以通过提取术语特征来识别关系，以将关系项与非关系术语区分开来，识别每个相邻术语的坐标关系; 基于术语特征和词典语法模式识别其他相邻术语的短距离本体论（例如，超音阶或部分整体关系）; 然后根据确定的协调关系和短距离关系推断出长距离超高和部分整体关系。