利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

620 条记录 (耗时 0.02 秒)

    SPEECH ANALYSIS SYSTEM
    83.
    发明公开
    SPEECH ANALYSIS SYSTEM 失效
    语音分析系统

    公开(公告)号：EP0970463A1

    公开(公告)日：2000-01-12

    申请号：EP98907075.0

    申请日：1998-02-26

    申请人： THE SECRETARY OF STATE FOR DEFENCE

    发明人： SERIES, Robert, William

    IPC分类号： G10L3/00

    CPC分类号： G10L15/065 ,  G10L15/142 ,  G10L15/20

    摘要： A speech analysis system (10) incorporates a filterbank analyser (18) producing successive frequency data vectors for a speech signal from two speakers. From each data vector, units (22A and 22B) produce a set of modified data vectors compensated for differing forms of distortion associated with respective speakers. A computer (24) matches modified data vectors to hidden Markov model states. It identifies the modified data vector in each set exhibiting greatest matching probability, the model state matched therewith, the form of distortion with which it is associated and the model class, i.e. speech or noise. The matched model state has a mean value providing an estimate of its associated data vector. The estimate is compared with its associated data vector, and their difference is averaged with others associated with a like form of distortion in an infinite response filter bank (48A or 48B) to provide compensation for that form of distortion. Averaged difference vectors provide compensation for multiple forms of distortion associated with respective speakers.

    摘要翻译： 一个语音分析系统（10）包括一个滤波器组分析器（18），它产生来自两个扬声器的语音信号的连续频率数据矢量。 从每个数据矢量，单元（22A和22B）产生一组修正的数据矢量，补偿与各个扬声器相关的不同形式的失真。 计算机（24）将修改后的数据向量与隐马尔可夫模型状态进行匹配。 它识别每个集合中具有最大匹配概率，与之匹配的模型状态，与其相关联的失真形式以及模型类别（即语音或噪声）的修改数据向量。 匹配的模型状态具有提供其相关数据向量的估计的平均值。 将估计值与其相关数据向量进行比较，并将它们的差值与其他与无限响应滤波器组（48A或48B）中的相似失真形式相关联的差值进行平均，以针对该失真形式提供补偿。 平均差异向量为与各个讲话者相关联的多种形式的失真提供补偿。

    METHOD AND RECOGNIZER FOR RECOGNIZING A SAMPLED SOUND SIGNAL IN NOISE
    84.
    发明公开
    METHOD AND RECOGNIZER FOR RECOGNIZING A SAMPLED SOUND SIGNAL IN NOISE 失效
    方法和设备识别噪音信号样本从噪声

    公开(公告)号：EP0950239A1

    公开(公告)日：1999-10-20

    申请号：EP97915156.0

    申请日：1997-03-06

    申请人： MOTOROLA, INC.

    发明人： FINEBERG, Adam, B.

    IPC分类号： G10L15

    CPC分类号： G10L15/20 ,  G10L15/02

    摘要： A sound recognizer uses a feature value normalization process to substantially increase the accuracy of recognizing acoustic signals in noise. The sound recognizer includes a feature vector device (110) which determines a number of feature values for a number of analysis frames, a min/max device (120) which determines a minimum and maximum feature value for each of a number of frequency bands, a normalizer (130) which normalizes each of the feature values with the minimum and maximum feature values resulting in normalized feature vectors, and a comparator (140) which compares the normalized feature vectors with template feature vectors to identify one of the template feature vectors that most resembles the normalized feature vectors.

    Speech processor
    87.
    发明授权
    Speech processor 失效
    语音处理

    公开(公告)号：EP0750291B1

    公开(公告)日：1999-08-04

    申请号：EP93203407.7

    申请日：1987-05-29

    申请人： BRITISH TELECOMMUNICATIONS public limited company

    发明人： Forse, Nicholas John Arnold

    IPC分类号： G10L3/00

    CPC分类号： G10L15/20 ,  G10L15/00 ,  G10L25/18 ,  G10L25/78 ,  G10L2021/02168

    摘要： In a speech processor such as a speech recogniser, the problem of distortion of extracted features caused by adaption of the input automatic gain control (AGC) during feature extraction is solved by storing the AGC's gain coefficient along with the energy level of each extracted feature. At the end of the sampling period the stored gain coefficients are set equal to the minimum stored coefficient and the associated energy levels adjusted accordingly. The AGC circuit may comprise a digitally switched attenuator under the control of a microprocessor performing the speech recognition.

    Speech recognition method and speech recognition apparatus
    88.
    发明公开
    Speech recognition method and speech recognition apparatus 有权
    Verfahren und Vorrichtung zur Spracherkennung

    公开(公告)号：EP0911805A2

    公开(公告)日：1999-04-28

    申请号：EP98120007.4

    申请日：1998-10-22

    申请人： PIONEER ELECTRONIC CORPORATION

    发明人： Ishimitsu, Shunsuke, c/o Pioneer Electronic Corp.

    IPC分类号： G10L3/00

    CPC分类号： G10L15/065 ,  G10L15/20 ,  G10L21/0216 ,  G10L25/24

    摘要： A speech recognition method of recognizing an input speech in a noisy environment by using a plurality of clean speech models is provided. Each of the clean speech models has a clean speech feature parameter S representing a cepstrum parameter of a clean speech thereof. The speech recognition method has the processes of: detecting a noise feature parameter N representing a cepstrum parameter of a noise in the noisy environment, immediately before the input speech is input; detecting an input speech feature parameter X representing a cepstrum parameter of the input speech in the noisy environment; calculating a modified clean speech feature parameter Y according to a following equation: Y = k · S + (1-k) · N (0 where the "k" is a predetermined value corresponding to a signal-to-noise ratio in the noise environment; comparing the input speech feature parameter X with the modified clean speech feature parameter Y; and recognizing the input speech by repeatedly carrying out the calculating process and the comparing process with respect to the plurality of clean speech models.

    摘要翻译： 提供了一种通过使用多个清晰语音模型在噪声环境中识别输入语音的语音识别方法。 每个清洁语音模型具有表示其干净语音的倒谱参数的干净的语音特征参数S。 语音识别方法具有以下处理：在输入语音输入之前，检测表示噪声环境中的噪声的倒谱参数的噪声特征参数N; 在噪声环境中检测表示输入语音的倒谱参数的输入语音特征参数X; 根据以下等式计算经修改的干净语音特征参数Y：其中“k”是对应于噪声环境中的信噪比的预定值; 将输入语音特征参数X与修改后的清晰语音特征参数Y进行比较; 以及通过反复执行关于多个清洁语音模型的计算处理和比较处理来识别输入语音。