知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

63 条记录 (耗时 0.016 秒)

    Method for task classification using morphemes
    33.
    发明授权
    Method for task classification using morphemes 有权
    使用语素进行任务分类的方法

    公开(公告)号：US07085720B1

    公开(公告)日：2006-08-01

    申请号：US09690721

    申请日：2000-10-18

    申请人： Allen Louis Gorin ,  Dijana Petrovska-Delacretaz ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    发明人： Allen Louis Gorin ,  Dijana Petrovska-Delacretaz ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    IPC分类号： G10L15/18

    CPC分类号： G10L15/1822 ,  G10L15/02 ,  G10L15/1815 ,  G10L15/24

    摘要： The invention concerns a method of task classification using morphemes which operates on the task objective of a user. The morphemes may be generated by clustering selected ones of the salient sub-morphemes selected from training speech which are semantically and syntactically similar. The method may include detecting morphemes present in the user's input communication, and making task-type classification decisions based on the detected morphemes in the user's input communication. The morphemes may be verbal and/or non-verbal.

    摘要翻译： 本发明涉及使用对用户的任务目标进行操作的语素的任务分类方法。 语素可以通过聚类从语义和语法上相似的训练语音中选出的突出的子语素中产生。 该方法可以包括检测用户输入通信中存在的语素，并且基于用户输入通信中检测到的语素来进行任务类型分类决定。 语素可能是口头和/或非言语。

    Method for generating morphemes
    34.
    发明授权
    Method for generating morphemes 有权
    生成语素的方法

    公开(公告)号：US06681206B1

    公开(公告)日：2004-01-20

    申请号：US09690903

    申请日：2000-10-18

    申请人： Allen Louis Gorin ,  Dijana Petrovska-Delacretaz ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    发明人： Allen Louis Gorin ,  Dijana Petrovska-Delacretaz ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    IPC分类号： G10L1506

    CPC分类号： G06F17/2755

    摘要： The invention concerns a method of generating morphemes for speech recognition and understanding. The method may include receiving training speech, selecting candidate sub-morphemes from the training speech, selecting salient sub-morphemes from the candidate sub-morphemes based on salience measurements, and clustering the salient sub-morphemes based on semantic and syntactic similarities into morphemes. The morphemes may be acoustic and/or non-acoustic. The sub-morphemes may represent any sub-unit of communication including phones, phone-phrases, grammars, diphones, words, gestures, tablet strokes, body movements, mouse clicks, etc. The training speech may be verbal, non-verbal, a combination of verbal and non-verbal, or multimodal.

    摘要翻译： 本发明涉及一种产生用于语音识别和理解的语素的方法。 该方法可以包括接收训练语音，从训练语音中选择候选子语素，基于显着性测量从候选子语素中选择突出的子语素，并将基于语义和句法相似性的突出子语素聚类成语素。 语素可以是声学和/或非声学的。 子语素可以代表任何通信的子单元，包括手机，电话短语，语法，双音，单词，手势，平板笔画，身体动作，鼠标点击等。训练语音可以是口头上，非口头的，一个 口头和非言语或多式联运。

    Automatic clustering of tokens from a corpus for grammar acquisition
    35.
    发明授权
    Automatic clustering of tokens from a corpus for grammar acquisition 有权
    用于语法获取的语料库的令牌的自动聚类

    公开(公告)号：US06317707B1

    公开(公告)日：2001-11-13

    申请号：US09207326

    申请日：1998-12-07

    申请人： Srinivas Bangalore ,  Giuseppe Riccardi

    发明人： Srinivas Bangalore ,  Giuseppe Riccardi

    IPC分类号： G06F1727

    CPC分类号： G06F17/274 ,  G06F17/2765 ,  G06F17/277 ,  G06K9/6282

    摘要： In a method of learning grammar from a corpus, context words are identified from a corpus. For the other non-context words, the method counts the occurrence of predetermined relationships which the context words, and maps the counted occurrences to a multidimensional frequency space. Clusters are grown from the frequency vectors. The clusters represent classes of words; words in the same cluster possess the same lexical significancy and provide an indicator of grammatical structure.

    摘要翻译： 在从语料库学习语法的方法中，从语料库中识别语境词。 对于其他非上下文单词，该方法计算上下文单词的预定关系的发生，并将计数的出现映射到多维频率空间。 群体从频率向量生长。 集群表示单词类; 同一集群中的词具有相同的词汇意义，并提供了语法结构的指标。

    Selection of superwords based on criteria relevant to both speech recognition and understanding
    36.
    发明授权
    Selection of superwords based on criteria relevant to both speech recognition and understanding 失效
    基于与语音识别和理解相关的标准选择词条

    公开(公告)号：US6044337A

    公开(公告)日：2000-03-28

    申请号：US960289

    申请日：1997-10-29

    申请人： Allen Louis Gorin ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    发明人： Allen Louis Gorin ,  Giuseppe Riccardi ,  Jeremy Huntley Wright

    IPC分类号： G10L15/18 ,  G06F17/28 ,  G10L5/06 ,  G10L9/00

    CPC分类号： G10L15/18 ,  G10L15/197

    摘要： This invention is directed to the selection of superwords based on a criterion relevant to speech recognition and understanding. Superwords are used to refer to those word combinations which are so often spoken that are recognized or should have models for such combinations reflected in its grammar. The selected superwords are placed in a lexicon is then used by a speech recognizer to improve recognition of input speech utterances for the proper routing of a user's task objectives.

    摘要翻译： 本发明旨在基于与语音识别和理解相关的标准来选择词条。 超级词汇被用来指经常被发音的那些单词组合，这些单词组合被识别出来，或者应该具有反映在其语法中的组合的模型。 所选择的词语被放置在词典中，然后由语音识别器使用，以改善输入语音话语的识别，以便正确地路由用户的任务目标。

    Grammar fragment acquisition using syntactic and semantic clustering
    37.
    发明授权
    Grammar fragment acquisition using syntactic and semantic clustering 失效
    使用语法和语义聚类的语法片段获取

    公开(公告)号：US08666744B1

    公开(公告)日：2014-03-04

    申请号：US09666563

    申请日：2000-09-21

    申请人： Kazuhiro Arai ,  Allen L. Gorin ,  Giuseppe Riccardi ,  Jeremy H. Wright

    发明人： Kazuhiro Arai ,  Allen L. Gorin ,  Giuseppe Riccardi ,  Jeremy H. Wright

    IPC分类号： G10L15/00

    CPC分类号： G10L15/063 ,  G06F17/274 ,  G10L15/193 ,  G10L2015/0631

    摘要： A method and apparatus are provided for automatically acquiring grammar fragments for recognizing and understanding fluently spoken language. Grammar fragments representing a set of syntactically and semantically similar phrases may be generated using three probability distributions: of succeeding words, of preceding words, and of associated call-types. The similarity between phrases may be measured by applying Kullback-Leibler distance to these three probability distributions. Phrases being close in all three distances may be clustered into a grammar fragment.

    摘要翻译： 提供了一种方法和装置，用于自动获取用于识别和理解流利的口语的语法片段。 可以使用三个概率分布来生成代表一组语法和语义上类似的短语的语法片段：前一个单词的后续单词和相关联的呼叫类型。 可以通过将Kullback-Leibler距离应用于这三个概率分布来测量短语之间的相似性。 所有三个距离中的短语可能被聚集成语法片段。

    Recognizing the numeric language in natural spoken dialogue
    38.
    发明授权
    Recognizing the numeric language in natural spoken dialogue 有权
    认识到自然语言对话中的数字语言

    公开(公告)号：US08655658B2

    公开(公告)日：2014-02-18

    申请号：US13280884

    申请日：2011-10-25

    申请人： Mazin G. Rahim ,  Giuseppe Riccardi ,  Jeremy Huntley Wright ,  Bruce Melvin Buntschuh ,  Allen Louis Gorin

    发明人： Mazin G. Rahim ,  Giuseppe Riccardi ,  Jeremy Huntley Wright ,  Bruce Melvin Buntschuh ,  Allen Louis Gorin

    IPC分类号： G10L15/14 ,  G10L15/18

    CPC分类号： G10L15/142

    摘要： A system and a method are provided. A speech recognition processor receives unconstrained input speech and outputs a string of words. The speech recognition processor is based on a numeric language that represents a subset of a vocabulary. The subset includes a set of words identified as being for interpreting and understanding number strings. A numeric understanding processor contains classes of rules for converting the string of words into a sequence of digits. The speech recognition processor utilizes an acoustic model database. A validation database stores a set of valid sequences of digits. A string validation processor outputs validity information based on a comparison of a sequence of digits output by the numeric understanding processor with valid sequences of digits in the validation database.

    摘要翻译： 提供了一种系统和方法。 语音识别处理器接收无约束输入语音并输出一串字。 语音识别处理器基于代表词汇子集的数字语言。 该子集包括被识别为用于解释和理解数字串的一组单词。 数字理解处理器包含用于将字符串转换为数字序列的规则类型。 语音识别处理器利用声学模型数据库。 验证数据库存储一组有效的数字序列。 字符串验证处理器基于数字理解处理器输出的数字序列与验证数据库中的有效数字序列的比较来输出有效性信息。