会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明申请
    • LANGUAGE MODEL TRAINED USING PREDICTED QUERIES FROM STATISTICAL MACHINE TRANSLATION
    • 使用来自统计机器翻译的预测性问题的语言模型
    • WO2014190220A2
    • 2014-11-27
    • PCT/US2014/039258
    • 2014-05-23
    • MICROSOFT CORPORATION
    • LEVIT, MichaelHAKKANI-TUR, DilekTUR, Gokhan
    • G10L15/06
    • G10L15/063G06F17/2818G06F17/30023G06F17/30976G10L15/197
    • A Statistical Machine Translation (SMT) model is trained using pairs of sentences that include content obtained from one or more content sources (e.g. feed(s)) with corresponding queries that have been used to access the content. A query click graph may be used to assist in determining candidate pairs for the SMT training data. All/portion of the candidate pairs may be used to train the SMT model. After training the SMT model using the SMT training data, the SMT model is applied to content to determine predicted queries that may be used to search for the content. The predicted queries are used to train a language model, such as a query language model. The query language model may be interpolated other language models, such as a background language model, as well as a feed language model trained using the content used in determining the predicted queries.
    • 使用成对的句子来训练统计机器翻译(SMT)模型,所述句子包括从一个或多个内容源(例如,馈送)获得的内容与已经用于访问内容的对应查询。 可以使用查询点击图来帮助确定SMT训练数据的候选对。 候选对的全部/部分可用于训练SMT模型。 在使用SMT培训数据对SMT模型进行培训后,将SMT模型应用于内容,以确定可能用于搜索内容的预测查询。 预测的查询用于训练语言模型,如查询语言模型。 查询语言模型可以内插其他语言模型,例如背景语言模型,以及使用在确定预测查询中使用的内容训练的馈送语言模型。
    • 3. 发明申请
    • MULTIPLE RECOGNIZER SPEECH RECOGNITION
    • 多种识别语音识别
    • WO2014186090A1
    • 2014-11-20
    • PCT/US2014/034686
    • 2014-04-18
    • GOOGLE INC.
    • ALEKSIC, PetarMORENO MENGIBAR, Pedro J.BIADSY, Fadi
    • G10L15/32G10L15/197G10L15/30
    • G10L15/26G10L15/01G10L15/197G10L15/30G10L15/32H04M2250/74
    • The subject matter of this specification can be embodied in, among other things, a method that includes receiving audio data that corresponds to an utterance, obtaining a first transcription of the utterance that was generated using a limited speech recognizer. The limited speech recognizer includes a speech recognizer that includes a language model that is trained over a limited speech recognition vocabulary that includes one or more terms from a voice command grammar, but that includes fewer than all terms of an expanded grammar. A second transcription of the utterance is obtained that was generated using an expanded speech recognizer. The expanded speech recognizer includes a speech recognizer that includes a language model that is trained over an expanded speech recognition vocabulary that includes all of the terms of the expanded grammar. The utterance is classified based at least on a portion of the first transcription or the second transcription.
    • 本说明书的主题可以包括接收对应于话语的音频数据的方法,获得使用有限语音识别器产生的话语的第一次转录。 有限语音识别器包括语音识别器,该语音识别器包括一个语言模型,该语言模型通过有限的语音识别词汇训练,该语义识别词汇包括来自语音命令语法的一个或多个术语,但是包括扩展语法的全部术语。 获得了使用扩展语音识别器生成的话语的第二个转录。 扩展语音识别器包括语音识别器,其包括在包括扩展语法的所有术语的扩展语音识别词汇训练的语言模型。 该话语至少基于第一转录或第二转录的一部分进行分类。
    • 4. 发明申请
    • METHOD AND SYSTEM FOR AUTOMATIC SPEECH RECOGNITION
    • 自动语音识别方法与系统
    • WO2014117555A1
    • 2014-08-07
    • PCT/CN2013/086707
    • 2013-11-07
    • TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    • RAO, FengLU, LiCHEN, BoYUE, ShuaiZHANG, XiangWANG, EryuXIE, DadongLI, LouLU, Duling
    • G10L15/00G10L15/02G10L15/14G10L15/22G10L15/26
    • G10L15/197
    • An automatic speech recognition method includes at a computer having one or more processors and a memory for storing one or more programs to be executed by the processors, obtaining a plurality of speech corpus categories through classifying and calculating raw speech corpus (801); obtaining a plurality of classified language models that respectively correspond to the plurality of speech corpus categories through language model training applied on each speech corpus category (802); obtaining an interpolation language model through implementing a weighted interpolation on each classified language model and merging the interpolated plurality of classified language models (803); constructing a decoding resource in accordance with an acoustic model and the interpolation language model (804); decoding input speech using the decoding resource, and outputting a character string with a highest probability as the recognition result of the input speech (805).
    • 自动语音识别方法包括在具有一个或多个处理器的计算机和用于存储要由处理器执行的一个或多个程序的存储器,通过分类和计算原始语音语料库(801)获得多个语音语料库类别; 通过在每个语音语料库类别(802)上应用的语言模型训练获得分别对应于多个语音语料库类别的多个分类语言模型; 通过对每个分类语言模型实施加权内插并合并内插多个分类语言模型(803)来获得内插语言模型; 根据声学模型和内插语言模型构造解码资源(804); 使用解码资源解码输入语音,并输出具有最高概率的字符串作为输入语音的识别结果(805)。
    • 6. 发明申请
    • CUSTOMIZED VOICE ACTION SYSTEM
    • 自定义语音处理系统
    • WO2013176855A2
    • 2013-11-28
    • PCT/US2013/039075
    • 2013-05-01
    • GOOGLE INC.
    • MENGIBAR, Pedro J. Moreno
    • G10L15/19
    • G10L15/22G06F17/2735G06Q30/0256G06Q30/0275G06Q30/0277G06Q30/08G10L15/08G10L15/197G10L2015/088G10L2015/223
    • Systems, methods, and computer-readable media that may be used to modify a voice action system to include voice actions provided by advertisers or users are provided. One method includes receiving electronic voice action bids from advertisers to modify the voice action system to include a specific voice action (e.g., a triggering phrase and an action). One or more bids may be selected. The method includes, for each of the selected bids, modifying data associated with the voice action system to include the voice action associated with the bid, such that the action associated with the respective voice action is performed when voice input from a user is received that the voice action system determines to correspond to the triggering phrase associated with the respective voice action.
    • 提供了可用于修改语音动作系统以包括由广告商或用户提供的语音动作的系统,方法和计算机可读介质。 一种方法包括从广告商接收电子语音动作出价以修改语音动作系统以包括特定语音动作(例如,触发短语和动作)。 可以选择一个或多个出价。 该方法包括对于每个所选择的出价,修改与语音动作系统相关联的数据以包括与出价相关联的语音动作,使得当接收到来自用户的语音输入时执行与相应语音动作相关联的动作, 语音动作系统确定对应于与相应语音动作相关联的触发短语。
    • 8. 发明申请
    • SYSTEM AND METHOD FOR ADAPTIVE AUTOMATIC ERROR CORRECTION
    • 用于自适应自动校正的系统和方法
    • WO2006113350A3
    • 2009-05-07
    • PCT/US2006013864
    • 2006-04-13
    • NUANCE COMMUNICATIONS INC
    • CARUS ALWIN BLAPSHINA LARISSARECHEA BERNARDOURHBACH AMY J
    • G10L15/20G10L15/00G10L15/18
    • G10L15/197G10L15/063G10L2015/0631
    • A method for adaptive automatic error and mismatch correction is disclosed for use with a system having an automatic error and mismatch correction learning module, an automatic error and mismatch correction model, and a classifier module. The learning module operates by receiving pairs of documents, identifying and selecting effective candidate errors and mismatches, and generating classifiers corresponding to these selected errors and mismatches. The correction model operates by receiving a string of interpreted speech into the automatic error and mismatch correction module, identifying target tokens in the string of interpreted speech, creating a set of classifier features according to requirements of the automatic error and mismatch correction model, comparing the target tokens against the classifier features to detect errors and mismatches in the string of interpreted speech, and modifying the string of interpreted speech based upon the classifier features.
    • 公开了一种用于具有自动错误和不匹配校正学习模块,自动错误和不匹配校正模型以及分类器模块的系统的自适应自动错误和不匹配校正的方法。 学习模块通过接收文档对,识别和选择有效的候选错误和不匹配来操作,以及生成与这些选择的错误和不匹配相对应的分类器。 校正模型通过将自动错误和不匹配校正模块中的解释语音串接收,识别解释语音串中的目标令牌,根据自动错误和不匹配校正模型的要求创建一组分类器特征,比较 针对分类器特征的目标标记来检测解释语音串中的错误和不匹配,以及基于分类器特征修改解释语音字符串。