利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

82 条记录 (耗时 0.024 秒)

    CONCATENATED EXPECTED RESPONSES FOR SPEECH RECOGNITION
    54.
    发明公开
    CONCATENATED EXPECTED RESPONSES FOR SPEECH RECOGNITION 审中-公开
    VERKETTETE ERWARTETE ANTWORTENFÜRSPRACHERKENNUNG

    公开(公告)号：EP3023980A1

    公开(公告)日：2016-05-25

    申请号：EP15192854.6

    申请日：2015-11-03

    申请人： Hand Held Products, Inc.

    发明人： BRAHO, Keith ,  MAKAY, Jason M.

    IPC分类号： G10L15/065 ,  G10L15/22

    CPC分类号： G10L15/22 ,  G06F17/2725 ,  G10L13/04 ,  G10L15/01 ,  G10L15/065 ,  G10L15/08 ,  G10L2015/088

    摘要： A speech recognition system used for hands-free data entry receives and analyzes speech input to recognize and accept a user's response. Under certain conditions, a user's response might be expected. In these situations, the expected response may modify the behavior of the speech recognition system to improve performance. For example, if the hypothesis of a user's response matches the expected response then there is a high probability that the user's response was recognized correctly. This information may be used to make adjustments. An expected response may include expected response parts, each part containing expected words. By considering an expected response as the concatenation of expected response parts, each part may be considered independently for the purposes of adjusting an acceptance algorithm, adjusting a model, or recording an apparent error. In this way, the speech recognition system may make modifications based on a wide range of user responses.

    摘要翻译： 用于免提数据输入的语音识别系统接收和分析语音输入以识别和接受用户的响应。 在某些情况下，可能会期待用户的回应。 在这些情况下，预期的响应可能会修改语音识别系统的行为以提高性能。 例如，如果用户的响应的假设与期望的响应相匹配，那么用户的响应被正确识别的概率很高。 此信息可用于进行调整。 期望的响应可以包括预期的响应部分，每个部分包含预期的单词。 通过考虑作为预期响应部分的级联的预期响应，为了调整接受算法，调整模型或记录明显误差，可以独立地考虑每个部分。 以这种方式，语音识别系统可以基于广泛的用户响应进行修改。

    METHOD AND SYSTEM FOR RECOGNIZING SPEECH USING WILDCARDS IN AN EXPECTED RESPONSE
    55.
    发明公开
    METHOD AND SYSTEM FOR RECOGNIZING SPEECH USING WILDCARDS IN AN EXPECTED RESPONSE 审中-公开
    VERFAHREN UND SYSTEM ZUR SPRACHERKENNUNG MIT PLATZHALTERN IN EINER ERWARTETEN ANTWORT

    公开(公告)号：EP3023979A1

    公开(公告)日：2016-05-25

    申请号：EP15191528.7

    申请日：2015-10-26

    申请人： Hand Held Products, Inc.

    发明人： BRAHO, Keith ,  MAKAY, Jason M.

    IPC分类号： G10L15/065 ,  G10L15/22

    CPC分类号： G10L15/07 ,  G10L15/065 ,  G10L15/22 ,  G10L25/51 ,  G10L2015/088

    摘要： A speech recognition system used in a workflow receives and analyzes speech input to recognize and accept a user's response to a task. Under certain conditions, a user's response might be expected. In these situations, the expected response may modify the behavior of the speech recognition system to improve recognition accuracy. For example, if the hypothesis of a user's response matches the expected response then there is a high probability that the user's response was recognized correctly. An expected response may include expected words and wildcard words. Wildcard words represent any recognized word in a user's response. By including wildcard words in the expected response, the speech recognition system may make modifications based on a wide range of user responses.

    摘要翻译： 工作流中使用的语音识别系统接收和分析语音输入以识别和接受用户对任务的响应。 在某些情况下，可能会期待用户的回应。 在这些情况下，预期的响应可以修改语音识别系统的行为以提高识别精度。 例如，如果用户的响应的假设与期望的响应相匹配，那么用户的响应被正确识别的概率很高。 预期的响应可以包括预期的单词和通配符词。 通配符字表示用户响应中的任何识别的字。 通过在期望的响应中包含通配符字，语音识别系统可以基于广泛的用户响应进行修改。

    METHOD OF PROVIDING VOICE COMMAND AND ELECTRONIC DEVICE SUPPORTING THE SAME
    56.
    发明公开
    METHOD OF PROVIDING VOICE COMMAND AND ELECTRONIC DEVICE SUPPORTING THE SAME 审中-公开
    方法提供语音命令和电子设备的支持THEREOF

    公开(公告)号：EP2963642A1

    公开(公告)日：2016-01-06

    申请号：EP15174352.3

    申请日：2015-06-29

    申请人： Samsung Electronics Co., Ltd

    发明人： SUBHOJIT, Chakladar ,  LEE, Sang Hoon ,  LEE, Ji Min

    IPC分类号： G10L15/065 ,  G10L15/22 ,  G10L15/30 ,  G10L15/183

    CPC分类号： G10L15/22 ,  G10L15/06 ,  G10L15/065 ,  G10L15/183 ,  G10L15/30 ,  G10L2015/223

    摘要： An electronic device, a method, and a chip set are provided. The electronic device includes a memory configured to store at least one of audio feature data of audio data and speech recognition data obtained by speech recognition of audio data; and a control module connected to the memory, wherein the control module is configured to update a voice command that is set to execute a function through voice, the function being selected based on at least one of the audio feature data, the speech recognition data, and function execution data executed in relation to the audio data.

    摘要翻译： 本发明提供一种电子设备，方法和芯片组。 该电子设备包括被配置为存储由音频数据的语音识别获得的音频数据和语音识别数据的音频特征数据中的至少一个存储器; 和连接到所述存储器，worin所述控制模块被配置为更新的语音命令并设定通过语音来执行的功能的控制模块，基于所述音频特征数据，语音识别数据中的至少一个选择的功能， 和相对于所述音频数据来执行功能的执行数据。

    METHODS AND SYSTEMS FOR PROVIDING SPEECH RECOGNITION SYSTEMS BASED ON SPEECH RECORDINGS LOGS
    57.
    发明公开
    METHODS AND SYSTEMS FOR PROVIDING SPEECH RECOGNITION SYSTEMS BASED ON SPEECH RECORDINGS LOGS 审中-公开
    方法和系统提供语音识别系统基于语音记录日志

    公开(公告)号：EP2941768A1

    公开(公告)日：2015-11-11

    申请号：EP13826817.2

    申请日：2013-12-20

    申请人： Google Inc.

    发明人： MENGIBAR, Pedro J., Moreno ,  WEINSTEIN, Eugene

    IPC分类号： G10L15/065

    CPC分类号： G10L15/065 ,  G10L15/32 ,  G10L2015/0636

    摘要： Examples of methods and systems for providing speech recognition systems based on speech recordings logs are described. In some examples, a method may be performed by a computing device within a system to generate modified data logs to use as a training data set for an acoustic model for a particular language. A device may receive one or more data logs that comprise at least one or more recordings of spoken queries and transcribe the recordings. Based on comparisons, the device may identify any transcriptions that may be indicative of noise and may remove those transcriptions indicative of noise from the data logs. Further, the device may remove unwanted transcriptions from the data logs and the device may provide the modified data logs as a training data set to one or more acoustic models for particular languages.

    摘要翻译： 的方法和系统，用于提供基于语音的录音记录的语音识别系统的实例进行描述。 在一些实例中，一种方法可以由计算设备的系统内执行，以生成修改后的数据记录到在声学模型作为锻炼数据集使用用于特定语言。 设备可以接收一个或多个数据记录中做了口语查询至少包含一种或多种录音和转录录音。 基于比较，设备可以识别任何转录确实可以指示噪声的并且可以去除这些转录指示从所述数据记录的噪声。 此外，设备可以从数据日志删除不想要的转录和该装置可以作为一个锻炼数据设置为特定语言的一个或多个声学模型提供修改后的数据的日志。

    DETERMINING DIALOG STATES FOR LANGUAGE MODELS
    60.
    发明公开
    DETERMINING DIALOG STATES FOR LANGUAGE MODELS 审中-公开

    公开(公告)号：EP4235647A3

    公开(公告)日：2023-10-18

    申请号：EP23179644.2

    申请日：2016-11-30

    申请人： Google LLC

    发明人： ALEKSIC, Petar ,  MENGIBAR, Pedro J. Moreno

    IPC分类号： G10L15/22 ,  G10L15/065 ,  G10L15/197 ,  G10L15/183

    摘要： A computer-implemented method, comprising: receiving, by a computing device, audio data for a voice input to the computing device, wherein the voice input corresponds to an unknown stage of a multi-stage voice dialog between the computing device and a user of the computing device; determining an estimate for the unknown stage of the multi-stage voice dialog; providing, to a voice dialog system, (i) the audio data for the voice input to the computing device and (ii) an indication of the estimate for the unknown stage of the multi-stage voice dialog; obtaining, by the computing device and from the voice dialog system, a transcription of the voice input, wherein the transcription was generated by processing the audio data with a model that was biased according to parameters that correspond to a particular prediction for the unknown stage of the multi-stage voice dialog, wherein the voice dialog system is configured to determine the particular prediction for the unknown stage of the multi-stage voice dialog based on (i) the estimate for the unknown stage of the multi-stage voice dialog and (ii) additional information that indicates a context of the voice input; and presenting the transcription of the voice input with the computing device.