USE OF METADATA TO POST PROCESS SPEECH RECOGNITION OUTPUT
    11.
    发明申请
    USE OF METADATA TO POST PROCESS SPEECH RECOGNITION OUTPUT 有权
    使用元数据来过程语音识别输出

    公开(公告)号:US20090248415A1

    公开(公告)日:2009-10-01

    申请号:US12415874

    申请日:2009-03-31

    CPC分类号: G10L15/30 G10L2015/228

    摘要: A method of utilizing metadata stored in a computer-readable medium to assist in the conversion of an audio stream to a text stream. The method compares personally identifiable data, such as a user's electronic address book and/or Caller/Recipient ID information (in the case of processing voice mail to text), to the n-best results generated by a speech recognition engine for each word that is output by the engine. A goal of this comparison is to correct a possible misrecognition of a spoken proper noun such as a name or company with its proper textual form or a spoken phone number to correctly formatted phone number with Arabic numerals to improve the overall accuracy of the output of the voice recognition system.

    摘要翻译: 利用存储在计算机可读介质中的元数据来帮助将音频流转换成文本流的方法。 该方法将个人识别数据(例如用户的电子地址簿和/或来电/收件人ID信息(在处理语音邮件到文本的情况下))与由语音识别引擎为每个单词产生的n最佳结果进行比较, 由发动机输出。 这个比较的目标是纠正一个口头的专有名词,例如具有适当的文本形式或口头电话号码的名称或公司,以正确格式化的电话号码与阿拉伯数字的错误识别,以提高输出的总体准确性 语音识别系统

    Use of metadata to post process speech recognition output
    12.
    发明授权
    Use of metadata to post process speech recognition output 有权
    使用元数据来发布过程语音识别输出

    公开(公告)号:US08676577B2

    公开(公告)日:2014-03-18

    申请号:US12415874

    申请日:2009-03-31

    IPC分类号: G10L15/00

    CPC分类号: G10L15/30 G10L2015/228

    摘要: A method of utilizing metadata stored in a computer-readable medium to assist in the conversion of an audio stream to a text stream. The method compares personally identifiable data, such as a user's electronic address book and/or Caller/Recipient ID information (in the case of processing voice mail to text), to the n-best results generated by a speech recognition engine for each word that is output by the engine. A goal of this comparison is to correct a possible misrecognition of a spoken proper noun such as a name or company with its proper textual form or a spoken phone number to correctly formatted phone number with Arabic numerals to improve the overall accuracy of the output of the voice recognition system.

    摘要翻译: 利用存储在计算机可读介质中的元数据来帮助将音频流转换成文本流的方法。 该方法将个人识别数据(例如用户的电子地址簿和/或来电/收件人ID信息(在处理语音邮件到文本的情况下))与由语音识别引擎为每个单词产生的n最佳结果进行比较, 由发动机输出。 这个比较的目标是纠正一个口头的专有名词,例如具有适当的文本形式或口头电话号码的名称或公司,以正确格式化的电话号码与阿拉伯数字的错误识别,以提高输出的总体准确性 语音识别系统

    CORRECTIVE FEEDBACK LOOP FOR AUTOMATED SPEECH RECOGNITION
    13.
    发明申请
    CORRECTIVE FEEDBACK LOOP FOR AUTOMATED SPEECH RECOGNITION 有权
    用于自动语音识别的纠正反馈环

    公开(公告)号:US20130024195A1

    公开(公告)日:2013-01-24

    申请号:US13621189

    申请日:2012-09-15

    IPC分类号: G10L15/26

    摘要: A method for facilitating the updating of a language model includes receiving, at a client device, via a microphone, an audio message corresponding to speech of a user; communicating the audio message to a first remote server; receiving, that the client device, a result, transcribed at the first remote server using an automatic speech recognition system (“ASR”), from the audio message; receiving, at the client device from the user, an affirmation of the result; storing, at the client device, the result in association with an identifier corresponding to the audio message; and communicating, to a second remote server, the stored result together with the identifier.

    摘要翻译: 一种便于更新语言模型的方法包括在客户端设备经由麦克风接收对应于用户语音的音频消息; 将音频消息传送到第一远程服务器; 从所述音频消息接收所述客户端设备,使用自动语音识别系统(ASR)在所述第一远程服务器处转录的结果; 在客户端设备从用户接收结果的肯定; 在客户端设备处存储与对应于音频消息的标识符相关联的结果; 以及与所述标识符一起与所述第二远程服务器通信所存储的结果。

    Corrective feedback loop for automated speech recognition
    14.
    发明授权
    Corrective feedback loop for automated speech recognition 有权
    用于自动语音识别的纠正反馈回路

    公开(公告)号:US08352264B2

    公开(公告)日:2013-01-08

    申请号:US12407502

    申请日:2009-03-19

    IPC分类号: G10L15/00 G10L15/14

    摘要: A method for facilitating the updating of a language model includes receiving, at a client device, via a microphone, an audio message corresponding to speech of a user; communicating the audio message to a first remote server; receiving, that the client device, a result, transcribed at the first remote server using an automatic speech recognition system (“ASR”), from the audio message; receiving, at the client device from the user, an affirmation of the result; storing, at the client device, the result in association with an identifier corresponding to the audio message; and communicating, to a second remote server, the stored result together with the identifier.

    摘要翻译: 一种便于更新语言模型的方法包括在客户端设备经由麦克风接收对应于用户语音的音频消息; 将音频消息传送到第一远程服务器; 从所述音频消息接收所述客户端设备,使用自动语音识别系统(ASR)在所述第一远程服务器处转录的结果; 在客户端设备从用户接收结果的肯定; 在客户端设备处存储与对应于音频消息的标识符相关联的结果; 以及与所述标识符一起与所述第二远程服务器通信所存储的结果。

    CORRECTIVE FEEDBACK LOOP FOR AUTOMATED SPEECH RECOGNITION
    15.
    发明申请
    CORRECTIVE FEEDBACK LOOP FOR AUTOMATED SPEECH RECOGNITION 有权
    用于自动语音识别的纠正反馈环

    公开(公告)号:US20090240488A1

    公开(公告)日:2009-09-24

    申请号:US12407502

    申请日:2009-03-19

    IPC分类号: G06F17/27 G10L15/00 G06F3/041

    摘要: A method for facilitating the updating of a language model includes receiving, at a client device, via a microphone, an audio message corresponding to speech of a user; communicating the audio message to a first remote server; receiving, that the client device, a result, transcribed at the first remote server using an automatic speech recognition system (“ASR”), from the audio message; receiving, at the client device from the user, an affirmation of the result; storing, at the client device, the result in association with an identifier corresponding to the audio message; and communicating, to a second remote server, the stored result together with the identifier.

    摘要翻译: 一种便于更新语言模型的方法包括在客户端设备经由麦克风接收对应于用户语音的音频消息; 将音频消息传送到第一远程服务器; 从所述音频消息接收使用自动语音识别系统(“ASR”)在所述第一远程服务器处转录的结果,所述客户端设备, 在客户端设备从用户接收结果的肯定; 在客户端设备处存储与对应于音频消息的标识符相关联的结果; 以及与所述标识符一起与所述第二远程服务器通信所存储的结果。