中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.008 seconds)

    METHOD AND SYSTEM OF ENVIRONMENT SENSITIVE AUTOMATIC SPEECH RECOGNITION
    1.
    发明申请
    METHOD AND SYSTEM OF ENVIRONMENT SENSITIVE AUTOMATIC SPEECH RECOGNITION 审中-公开
    环境敏感自动语音识别方法与系统

    公开(公告)号：WO2016153712A1

    公开(公告)日：2016-09-29

    申请号：PCT/US2016/019503

    申请日：2016-02-25

    Applicant: INTEL CORPORATION

    Inventor： RAVINDRAN, Binuraj ,  STEMMER, Georg ,  HOFER, Joachim

    IPC: G10L15/22 ,  G10L15/26

    CPC classification number: G10L15/20 ,  G10L15/083 ,  G10L15/285 ,  G10L25/48 ,  G10L2015/226

    Abstract: In a system of an environment-sensitive automatic speech recognition, a method includes steps for obtaining audio data including human speech, determining at least one characteristic of the environment in which the audio data was obtained, and modifying at least one parameter to be used to perform speech recognition depending on the characteristic.

    Abstract translation: 在环境敏感自动语音识别的系统中，一种方法包括获得包括人类语音的音频数据的步骤，确定获得音频数据的环境的至少一个特征，以及修改至少一个要使用的参数 根据特性进行语音识别。

    ADAPTIVE SPEECH ENDPOINT DETECTOR
    2.
    发明申请
    ADAPTIVE SPEECH ENDPOINT DETECTOR 审中-公开
    自适应语音端点检测器

    公开(公告)号：WO2018063652A1

    公开(公告)日：2018-04-05

    申请号：PCT/US2017/048980

    申请日：2017-08-29

    Applicant: INTEL CORPORATION

    Inventor： HOFER, Joachim ,  GEORGES, Munir

    IPC: G10L25/87 ,  G10L17/12 ,  G06F17/28 ,  G10L25/78

    CPC classification number: G10L15/04 ,  G10L15/07 ,  G10L15/22 ,  G10L25/87 ,  G10L2025/786

    Abstract: An embodiment of a speech endpoint detector apparatus may include a speech detector to detect a presence of speech in an electronic speech signal, a pause duration measurer communicatively coupled to the speech detector to measure a duration of a pause following a period of detected speech, an end of utterance detector communicatively coupled to the pause duration measurer to detect if the pause measured following the period of detected speech is greater than a pause threshold corresponding to an end of an utterance, and a pause threshold adjuster to adaptively adjust the pause threshold corresponding to an end of an utterance based on stored pause information. Other embodiments are disclosed and claimed.

    Abstract translation: 语音端点检测器装置的一个实施例可以包括：语音检测器，用于检测电子语音信号中语音的存在;暂停持续时间测量器，通信地耦合到语音检测器，以测量暂停的持续时间 在检测到的语音的一段时间之后，话语检测器的结束通信地耦合到暂停持续时间测量器，以检测在检测到的话音的时段之后测量的暂停是否大于对应于话语的结束的暂停阈值，以及暂停阈值调整器 基于存储的暂停信息自适应地调整对应于话语的结尾的暂停阈值。 其他实施例被公开和要求保护。

    METHOD AND SYSTEM OF RANDOM ACCESS COMPRESSION OF TRANSDUCER DATA FOR AUTOMATIC SPEECH RECOGNITION DECODING
    3.
    发明申请
    METHOD AND SYSTEM OF RANDOM ACCESS COMPRESSION OF TRANSDUCER DATA FOR AUTOMATIC SPEECH RECOGNITION DECODING 审中-公开
    用于自动语音识别解码的传感器数据的随机访问压缩方法和系统

    公开(公告)号：WO2016167902A1

    公开(公告)日：2016-10-20

    申请号：PCT/US2016/021483

    申请日：2016-03-09

    Applicant: INTEL CORPORATION

    Inventor： HOFER, Joachim

    IPC: G10L19/00 ,  G10L21/04 ,  G10L15/28

    CPC classification number: G10L15/08

    Abstract: A system, article, and method for decompressing transducer data for speech recognition comprise: determining a location of a compressed block in an array of compressed block of transducer-related data; determining the compression rate of individual compressed entries in the located compressed block; determining a key value to be applied to individual compressed entries of the located compressed block to obtain the uncompressed value of the entry; reading a compressed entry from the compressed block; and decompressing the compressed entry by applying the key value to the compressed entry.

    Abstract translation: 用于解压缩用于语音识别的换能器数据的系统，物品和方法包括：确定传感器相关数据的压缩块阵列中的压缩块的位置; 确定所定位的压缩块中各个压缩条目的压缩率; 确定要应用于所定位的压缩块的各个压缩条目的密钥值以获得条目的未压缩值; 从压缩块读取压缩条目; 并通过将密钥值应用于压缩条目来解压缩压缩条目。

Patent Agency Ranking