利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

189 条记录 (耗时 0.027 秒)

    VOICE RECOGNITION SYSTEM
    4.
    发明申请
    VOICE RECOGNITION SYSTEM 审中-公开

    公开(公告)号：US20180190293A1

    公开(公告)日：2018-07-05

    申请号：US15910872

    申请日：2018-03-02

    申请人： Google LLC

    发明人： Petar Aleksic ,  Pedro J. Moreno Mengibar

    IPC分类号： G10L15/26 ,  G06F17/30 ,  G10L15/04

    CPC分类号： G10L15/26 ,  G06F17/30755 ,  G10L15/04 ,  G10L15/183 ,  G10L15/19 ,  G10L15/197 ,  G10L15/22 ,  G10L2015/085

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for voice recognition. In one aspect, a method includes the actions of receiving a voice input; determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input: obtaining a first candidate transcription for a first segment of the voice input; determining one or more contexts associated with the first candidate transcription; adjusting a respective weight for each of the one or more contexts; and determining a second candidate transcription for a second segment of the voice input based in part on the adjusted weights; and providing the transcription of the plurality of segments of the voice input for output.

    DISAMBIGUATION OF VEHICLE SPEECH COMMANDS
    5.
    发明申请
    DISAMBIGUATION OF VEHICLE SPEECH COMMANDS 审中-公开

    公开(公告)号：US20170323635A1

    公开(公告)日：2017-11-09

    申请号：US15146256

    申请日：2016-05-04

    申请人： GM Global Technology Operations LLC

    发明人： Xufang ZHAO ,  Gaurav TALWAR

    IPC分类号： G10L15/08 ,  G10L25/54 ,  G06F3/16 ,  G10L15/22

    CPC分类号： G10L15/08 ,  G06F3/167 ,  G10L15/22 ,  G10L25/54 ,  G10L2015/085 ,  G10L2015/088 ,  G10L2015/223

    摘要： A system and method of recognizing speech in a vehicle. The method includes receiving a voice command at the vehicle via a microphone in the vehicle, and obtaining a recognition result from speech recognition performed on the received voice command. The recognition result may represent the voice command and be indicative of any of two or more available vehicle commands. The method may further include selecting one of the two or more available vehicle commands based on a secondary characteristic and an attribute of the selected one of the vehicle commands. The system may be implemented as vehicle electronics that include a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle, and a controller in communication with the microphone. The controller may be configured to perform speech recognition on the voice command and obtain a disambiguated recognition result.

    Methods, apparatus and computer programs for automatic speech recognition
    9.
    发明授权
    Methods, apparatus and computer programs for automatic speech recognition 有权
    用于自动语音识别的方法，装置和计算机程序

    公开(公告)号：US09502024B2

    公开(公告)日：2016-11-22

    申请号：US14191176

    申请日：2014-02-26

    申请人： Nuance Communications, Inc.

    发明人： John Brian Pickering ,  Timothy David Poultney ,  Benjamin Terrick Staniford ,  Matthew Whitbourne

    IPC分类号： G10L15/00 ,  G10L15/08

    CPC分类号： G10L15/08 ,  G10L2015/025 ,  G10L2015/085

    摘要： An automatic speech recognition (ASR) system includes a speech-responsive application and a recognition engine. The ASR system generates user prompts to elicit certain spoken inputs, and the speech-responsive application performs operations when the spoken inputs are recognized. The recognition engine compares sounds within an input audio signal with phones within an acoustic model, to identify candidate matching phones. A recognition confidence score is calculated for each candidate matching phone, and the confidence scores are used to help identify one or more likely sequences of matching phones that appear to match a word within the grammar of the speech-responsive application. The per-phone confidence scores are evaluated against predefined confidence score criteria (for example, identifying scores below a ‘low confidence’ threshold) and the results of the evaluation are used to influence subsequent selection of user prompts. One such system uses confidence scores to select prompts for targetted recognition training—encouraging input of sounds identified as having low confidence scores. Another system selects prompts to discourage input of sounds that were not easily recognized.

    摘要翻译： 自动语音识别（ASR）系统包括语音响应应用和识别引擎。 ASR系统产生用户提示以引出某些口语输入，并且语音响应应用程序在识别出口语输入时执行操作。 识别引擎将输入音频信号中的声音与声学模型中的电话进行比较，以识别候选匹配电话。 为每个候选匹配电话计算识别置信度分数，并且使用置信度分数来帮助识别似乎与语音响应应用程序的语法中的单词相匹配的一个或多个可能的匹配电话序列。 根据预定义的置信评分标准（例如，识别低于“低置信度”阈值的分数）评估每手机信心分数，并且评估结果用于影响用户提示的后续选择。 一个这样的系统使用置信分数来选择针对性识别训练的提示 - 鼓励被识别为具有低置信度分数的声音输入。 另一个系统选择提示来阻止不容易识别的声音输入。

    METHODS, APPARATUS AND COMPUTER PROGRAMS FOR AUTOMATIC SPEECH RECOGNITION
    10.
    发明申请
    METHODS, APPARATUS AND COMPUTER PROGRAMS FOR AUTOMATIC SPEECH RECOGNITION 有权
    方法，装置和计算机程序自动语音识别

    公开(公告)号：US20140249816A1

    公开(公告)日：2014-09-04

    申请号：US14191176

    申请日：2014-02-26

    申请人： Nuance Communications, Inc.

    发明人： John Brian Pickering ,  Timothy David Poultney ,  Benjamin Terrick Staniford ,  Matthew Whitbourne

    IPC分类号： G10L15/08

    CPC分类号： G10L15/08 ,  G10L2015/025 ,  G10L2015/085

    摘要： An automatic speech recognition (ASR) system includes a speech-responsive application and a recognition engine. The ASR system generates user prompts to elicit certain spoken inputs, and the speech-responsive application performs operations when the spoken inputs are recognised. The recognition engine compares sounds within an input audio signal with phones within an acoustic model, to identify candidate matching phones. A recognition confidence score is calculated for each candidate matching phone, and the confidence scores are used to help identify one or more likely sequences of matching phones that appear to match a word within the grammar of the speech-responsive application. The per-phone confidence scores are evaluated against predefined confidence score criteria (for example, identifying scores below a ‘low confidence’ threshold) and the results of the evaluation are used to influence subsequent selection of user prompts. One such system uses confidence scores to select prompts for targetted recognition training—encouraging input of sounds identified as having low confidence scores. Another system selects prompts to discourage input of sounds that were not easily recognised.

    摘要翻译： 自动语音识别（ASR）系统包括语音响应应用和识别引擎。 ASR系统产生用户提示以引出某些口语输入，并且语音响应应用程序在识别出口语输入时执行操作。 识别引擎将输入音频信号中的声音与声学模型中的电话进行比较，以识别候选匹配电话。 为每个候选匹配电话计算识别置信度分数，并且使用置信度分数来帮助识别似乎与语音响应应用程序的语法中的单词相匹配的一个或多个可能的匹配电话序列。 根据预定义的置信评分标准（例如，识别低于“低置信度”阈值的分数）评估每手机信心分数，并且评估结果用于影响用户提示的后续选择。 一个这样的系统使用置信分数来选择针对性识别训练的提示 - 鼓励被识别为具有低置信度分数的声音输入。 另一个系统选择提示来阻止不容易识别的声音输入。