利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.017 秒)

    Method and apparatus for large vocabulary continuous speech recognition using a hybrid phoneme-word lattice
    2.
    发明授权
    Method and apparatus for large vocabulary continuous speech recognition using a hybrid phoneme-word lattice 有权
    使用混合音素词格的大词汇连续语音识别的方法和装置

    公开(公告)号：US08831947B2

    公开(公告)日：2014-09-09

    申请号：US12941057

    申请日：2010-11-07

    申请人： Moshe Wasserblat ,  Ronen Laperdon ,  Dori Shapira

    发明人： Moshe Wasserblat ,  Ronen Laperdon ,  Dori Shapira

    IPC分类号： G10L15/00 ,  G10L15/28 ,  G10L15/04 ,  G10L15/08

    CPC分类号： G10L15/08

    摘要： A method and apparatus combining the advantages of phonetic search such as the rapid implementation and deployment and medium accuracy, comprising steps and components for receiving the audio signal captured in the call center environment, extracting a multiplicity of feature vectors from the audio signal, creating a phoneme lattice from the multiplicity of feature vectors wherein the phoneme lattice comprising one or more allophone and each allophone comprising two or more phonemes, creating a hybrid phoneme-word lattice from the phoneme lattice and extracting the word by analyzing the hybrid phoneme-Word lattice.

    摘要翻译： 一种结合语音搜索的优点的方法和装置，例如快速实现和部署以及中等精度，包括用于接收在呼叫中心环境中捕获的音频信号的步骤和组件，从音频信号中提取多个特征向量，创建一个 从多个特征向量的音素格子中，其中包括一个或多个异音素的音素晶格和包含两个或更多个音素的每个异音素，从音素晶格产生混合的音素单元格，并通过分析混合的音素-Word晶格提取单词。

    METHOD AND APPARATUS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
    4.
    发明申请
    METHOD AND APPARATUS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION 有权
    大容量连续语音识别的方法与装置

    公开(公告)号：US20120116766A1

    公开(公告)日：2012-05-10

    申请号：US12941057

    申请日：2010-11-07

    申请人： Moshe WASSERBLAT ,  Ronen Laperdon ,  Dori Shapira

    发明人： Moshe WASSERBLAT ,  Ronen Laperdon ,  Dori Shapira

    IPC分类号： G10L15/02

    CPC分类号： G10L15/08

    摘要： A method and apparatus combining the advantages of phonetic search such as the rapid implementation and deployment and medium accuracy, with the advantages of speech to text, including providing the full text of the audio and rapid search.The method and apparatus comprise steps or components for receiving the audio signal captured in the call center environment; extracting a multiplicity of feature vectors from the audio signal; creating a phoneme lattice from the multiplicity of feature vectors, the phoneme lattice comprising one or more allophone, each allophone comprising two or more phonemes; creating a hybrid phoneme-word lattice from the phoneme lattice; and extracting the word by analyzing the hybrid phoneme-word lattice.

    摘要翻译： 一种结合语音搜索优点的方法和装置，如快速实施和部署以及中等精度，具有语音到文本的优点，包括提供音频和快速搜索的全文。 该方法和装置包括用于接收在呼叫中心环境中捕获的音频信号的步骤或组件; 从音频信号中提取多个特征向量; 从特征向量的多个形成音素晶格，所述音素晶格包括一个或多个异音素，每个异音素包括两个或多个音素; 从音素格子创建混合音素单词格子; 并通过分析混合音素单词格来提取单词。

    METHODS AND APPARATUS FOR REAL-TIME INTERACTION ANALYSIS IN CALL CENTERS
    8.
    发明申请
    METHODS AND APPARATUS FOR REAL-TIME INTERACTION ANALYSIS IN CALL CENTERS 有权
    呼叫中心实时交互分析的方法与设备

    公开(公告)号：US20110307257A1

    公开(公告)日：2011-12-15

    申请号：US12797618

    申请日：2010-06-10

    申请人： Oren PEREG ,  Moshe WASSERBLAT ,  Yuval LUBOWICH ,  Ronen LAPERDON ,  Dori SHAPIRA ,  Vladislav FEIGIN ,  Oz FOX-KAHANA

    发明人： Oren PEREG ,  Moshe WASSERBLAT ,  Yuval LUBOWICH ,  Ronen LAPERDON ,  Dori SHAPIRA ,  Vladislav FEIGIN ,  Oz FOX-KAHANA

    IPC分类号： G06F15/00

    CPC分类号： G06Q10/063 ,  G06Q30/01 ,  G06Q30/0202 ,  G10L15/08 ,  G10L15/22 ,  G10L2015/081 ,  G10L2015/085

    摘要： A method and system for indicating in real time that an interaction is associated with a problem or issue, comprising: receiving a segment of an interaction in which a representative of the organization participates; extracting a feature from the segment; extracting a global feature associated with the interaction; aggregating the feature and the global feature; and classifying the segment or the interaction in association with the problem or issue by applying a model to the feature and the global feature. The method and system may also use features extracted from earlier segments within the interaction. The method and system can also evaluate the model based on features extracted from training interactions and manual tagging assigned to the interactions or segments thereof.

    摘要翻译： 一种用于实时地指示交互与问题或问题相关联的方法和系统，包括：接收所述组织的代表参与的交互的一部分; 从段中提取特征; 提取与交互相关联的全局特征; 聚合特征和全局特征; 并通过将模型应用于特征和全局特征来分类或与问题或问题相关联的交互。 方法和系统还可以使用在交互作用中从先前段提取的特征。 该方法和系统还可以基于从训练相互作用提取的特征和分配给其相互作用或分段的手动标记来评估模型。

    APPARATUS AND METHOD FOR ENHANCED SPEECH RECOGNITION
    9.
    发明申请
    APPARATUS AND METHOD FOR ENHANCED SPEECH RECOGNITION 审中-公开
    用于增强语音识别的装置和方法

    公开(公告)号：US20110004473A1

    公开(公告)日：2011-01-06

    申请号：US12497718

    申请日：2009-07-06

    申请人： Ronen Laperdon ,  Moshe Wasserblat ,  Shimrit Artzi ,  Yuval Lubowich

    发明人： Ronen Laperdon ,  Moshe Wasserblat ,  Shimrit Artzi ,  Yuval Lubowich

    IPC分类号： G10L15/06 ,  G10L15/04 ,  G10L17/00 ,  G06F17/30

    CPC分类号： G10L15/02 ,  G10L2015/025

    摘要： A method and apparatus for improving speech recognition results for an audio signal captured within an organization, comprising: receiving the audio signal captured by a capturing or logging device; extracting a phonetic feature and an acoustic feature from the audio signal; decoding the phonetic feature into a phonetic searchable structure; storing the phonetic searchable structure and the acoustic feature in an index; performing phonetic search for a word or a phrase in the phonetic searchable structure to obtain a result; activating an audio analysis engine which receives the acoustic feature to validate the result and obtain an enhanced result.

    摘要翻译： 一种用于改善在组织内捕获的音频信号的语音识别结果的方法和装置，包括：接收由捕获或记录装置捕获的音频信号; 从音频信号中提取语音特征和声学特征; 将语音特征解码成语音可搜索结构; 将语音可搜索结构和声学特征存储在索引中; 在语音搜索结构中执行语音搜索单词或短语以获得结果; 激活音频分析引擎，其接收声学特征以验证结果并获得增强的结果。