中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.016 seconds)

    Split matrix quantization with split vector quantization error compensation and selective enhanced processing for robust speech recognition
    2.
    发明授权
    Split matrix quantization with split vector quantization error compensation and selective enhanced processing for robust speech recognition 失效
    分割矩阵量化与分割矢量量化误差补偿和鲁棒语音识别的选择性增强处理

    公开(公告)号：US6067515A

    公开(公告)日：2000-05-23

    申请号：US957903

    申请日：1997-10-27

    Applicant: Lin Cong ,  Safdar M. Asghar

    Inventor： Lin Cong ,  Safdar M. Asghar

    IPC: G10L15/02 ,  G10L15/10 ,  G10L15/20 ,  G10L9/00

    CPC classification number: G10L15/02 ,  G10L15/10 ,  G10L15/20

    Abstract: A speech recognition system utilizes both split matrix and split vector quantizers as front ends to a second stage speech classifier such as hidden Markov models (HMMs) to, for example, efficiently utilize processing resources and improve speech recognition performance. Fuzzy split matrix quantization (FSMQ) exploits the "evolution" of the speech short-term spectral envelopes as well as frequency domain information, and fuzzy split vector quantization (FSVQ) primarily operates on frequency domain information. Time domain information may be substantially limited which may introduce error into the matrix quantization, and the FSVQ may provide error compensation. Additionally, acoustic noise influence may affect particular frequency domain subbands. This system also, for example, exploits the localized noise by efficiently allocating enhanced processing technology to target noise-affected input signal parameters and minimize noise influence. The enhanced processing technology includes a weighted LSP and signal energy related distance measure in training Linde-Buzo-Gray (LBG) algorithm and during recognition. Multiple codebooks may also be combined to form single respective codebooks for split matrix and split vector quantization to lower processing resources demand.

    Abstract translation: 语音识别系统利用分割矩阵和分割矢量量化器作为第二级语音分类器的前端，例如隐马尔可夫模型（HMM），以例如有效利用处理资源并改善语音识别性能。 模糊分割矩阵量化（FSMQ）利用语音短期频谱包络的​​“演化”以及频域信息，模糊分割矢量量化（FSVQ）主要对频域信息进行操作。 时域信息可能基本上受到限制，这可能会将错误引入到矩阵量化中，并且FSVQ可以提供误差补偿。 此外，声学噪声的影响可能会影响特定的频域子频带。 例如，该系统还通过有效地分配增强的处理技术来目标受噪声影响的输入信号参数并最小化噪声影响来利用局部噪声。 增强处理技术包括训练林德 - 布佐 - 格雷（LBG）算法和识别期间的加权LSP和信号能量相关距离测量。 多个码本也可以组合以形成用于分割矩阵和分割矢量量化的单个相应码本，以降低处理资源需求。

    Speech recognition system having a quantizer using a single robust codebook designed at multiple signal to noise ratios
    4.
    发明授权
    Speech recognition system having a quantizer using a single robust codebook designed at multiple signal to noise ratios 失效
    语音识别系统具有使用以多个信噪比设计的单个鲁棒码本的量化器

    公开(公告)号：US6003003A

    公开(公告)日：1999-12-14

    申请号：US883979

    申请日：1997-06-27

    Applicant: Safdar M. Asghar ,  Lin Cong

    Inventor： Safdar M. Asghar ,  Lin Cong

    IPC: G10L15/02 ,  G10L15/06 ,  G10L7/08

    CPC classification number: G10L15/02 ,  G10L2015/0631

    Abstract: In one embodiment, a speech recognition system is organized with a fuzzy matrix quantizer with a single codebook representing u codewords. The single codebook is designed with entries from u codebooks which are designed with respective words at multiple signal to noise ratio levels. Such entries are, in one embodiment, centroids of clustered training data. The training data is, in one embodiment, derived from line spectral frequency pairs representing respective speech input signals at various signal to noise ratios. The single codebook trained in this manner provides a codebook for a robust front end speech processor, such as the fuzzy matrix quantizer, for training a speech classifier such as a u hidden Markov models and a speech post classifier such as a neural network. In one embodiment, a fuzzy Viterbi algorithm is used with the hidden Markov models to describe the speech input signal probabilistically.

    Abstract translation: 在一个实施例中，语音识别系统由具有代表u码字的单个码本的模糊矩阵量化器组织。 单码本被设计为来自u码本的条目，其被设计为具有多个信噪比水平的相应字。 在一个实施例中，这样的条目是聚类训练数据的质心。 在一个实施例中，训练数据来自于以各种信噪比表示各个语音输入信号的线谱频率对。 以这种方式训练的单个码本提供用于训练语音分类器（诸如，隐藏的马尔可夫模型）和诸如神经网络的语音后分类器之类的鲁棒前端语音处理器（例如模糊矩阵量化器）的码本。 在一个实施例中，使用模糊维特比算法与隐马尔可夫模型概率地描述语音输入信号。

    Quantization using frequency and mean compensated frequency input data for robust speech recognition
    5.
    发明授权
    Quantization using frequency and mean compensated frequency input data for robust speech recognition 有权
    使用频率和平均补偿频率输入数据量化，用于鲁棒语音识别

    公开(公告)号：US06418412B1

    公开(公告)日：2002-07-09

    申请号：US09649737

    申请日：2000-08-28

    Applicant: Safdar M. Asghar ,  Lin Cong

    Inventor： Safdar M. Asghar ,  Lin Cong

    IPC: G10L1514

    CPC classification number: G10L15/20 ,  G10L15/02 ,  G10L15/144

    Abstract: A speech recognition system utilizes multiple quantizers to process frequency parameters and mean compensated frequency parameters derived from an input signal. The quantizers may be matrix and vector quantizer pairs, and such quantizer pairs may also function as front ends to a second stage speech classifiers such as hidden Markov models (HMMs) and/or utilizes neural network postprocessing to, for example, improve speech recognition performance. Mean compensating the frequency parameters can remove noise frequency components that remain approximately constant during the duration of the input signal. HMM initial state and state transition probabilities derived from common quantizer types and the same input signal may be consolidated to improve recognition system performance and efficiency. Matrix quantization exploits the “evolution” of the speech short-term spectral envelopes as well as frequency domain information, and vector quantization (VQ) primarily operates on frequency domain information. Time domain information may be substantially limited which may introduce error into the matrix quantization, and the VQ may provide error compensation. The matrix and vector quantizers may split spectral subbands to target selected frequencies for enhanced processing and may use fuzzy associations to develop fuzzy observation sequence data. A mixer may provide a variety of input data to the neural network for classification determination. Fuzzy operators may be utilized to reduce quantization error. Multiple codebooks may also be combined to form single respective codebooks for split matrix and split vector quantization to reduce processing resources demand.

    Abstract translation: 语音识别系统利用多个量化器来处理来自输入信号的频率参数和平均补偿频率参数。 量化器可以是矩阵和矢量量化器对，并且这样的量化器对还可以用作第二阶段语音分类器（例如隐马尔可夫模型（HMM））的前端，和/或利用神经网络后处理来例如改善语音识别性能 。 平均补偿频率参数可以消除在输入信号的持续时间内保持近似恒定的噪声频率分量。 可以整合从公共量化器类型和相同输入信号导出的HMM初始状态和状态转移概率，以提高识别系统的性能和效率。 矩阵量化利用语音短期频谱包络和频域信息的“演化”，矢量量化（VQ）主要对频域信息进行操作。 时域信息可能基本上受到限制，这可能会将错误引入到矩阵量化中，并且VQ可以提供误差补偿。 矩阵和矢量量化器可以将频谱子带分解成目标选择的频率用于增强处理，并且可以使用模糊关联来开发模糊观测序列数据。 混合器可以向神经网络提供各种输入数据以进行分类确定。 可以使用模糊算子来减少量化误差。 多个码本也可以组合以形成用于分割矩阵和分割矢量量化的单个相应码本，以减少处理资源需求。

    Quantization using frequency and mean compensated frequency input data for robust speech recognition
    8.
    发明授权
    Quantization using frequency and mean compensated frequency input data for robust speech recognition 有权
    使用频率和平均补偿频率输入数据量化，用于鲁棒语音识别

    公开(公告)号：US06219642B1

    公开(公告)日：2001-04-17

    申请号：US09166648

    申请日：1998-10-05

    Applicant: Safdar M. Asghar ,  Lin Cong

    Inventor： Safdar M. Asghar ,  Lin Cong

    IPC: G10L1514

    CPC classification number: G10L15/20 ,  G10L15/02 ,  G10L15/144

    Abstract: A speech recognition system utilizes multiple quantizers to process frequency parameters and mean compensated frequency parameters derived from an input signal. The quantizers may be matrix and vector quantizer pairs, and such quantizer pairs may also function as front ends to a second stage speech classifiers such as hidden Markov models (HMMs) and/or utilizes neural network postprocessing to, for example, improve speech recognition performance. Mean compensating the frequency parameters can remove noise frequency components that remain approximately constant during the duration of the input signal. HMM initial state and state transition probabilities derived from common quantizer types and the same input signal may be consolidated to improve recognition system performance and efficiency. Matrix quantization exploits the “evolution” of the speech short-term spectral envelopes as well as frequency domain information, and vector quantization (VQ) primarily operates on frequency domain information. Time domain information may be substantially limited which may introduce error into the matrix quantization, and the VQ may provide error compensation. The matrix and vector quantizers may split spectral subbands to target selected frequencies for enhanced processing and may use fuzzy associations to develop fuzzy observation sequence data. A mixer may provide a variety of input data to the neural network for classification determination. Fuzzy operators may be utilized to reduce quantization error. Multiple codebooks may also be combined to form single respective codebooks for split matrix and split vector quantization to reduce processing resources demand.

    Abstract translation: 语音识别系统利用多个量化器来处理来自输入信号的频率参数和平均补偿频率参数。 量化器可以是矩阵和矢量量化器对，并且这样的量化器对还可以用作第二阶段语音分类器（例如隐马尔可夫模型（HMM））的前端，和/或利用神经网络后处理来例如改善语音识别性能 。 平均补偿频率参数可以消除在输入信号的持续时间内保持近似恒定的噪声频率分量。 可以整合从公共量化器类型和相同输入信号导出的HMM初始状态和状态转移概率，以提高识别系统的性能和效率。 矩阵量化利用语音短期频谱包络和频域信息的“演化”，矢量量化（VQ）主要对频域信息进行操作。 时域信息可能基本上受到限制，这可能会将错误引入到矩阵量化中，并且VQ可以提供误差补偿。 矩阵和矢量量化器可以将频谱子带分解成目标选择的频率用于增强处理，并且可以使用模糊关联来开发模糊观测序列数据。 混合器可以向神经网络提供各种输入数据以进行分类确定。 可以使用模糊算子来减少量化误差。 多个码本也可以组合以形成用于分割矩阵和分割矢量量化的单个相应码本，以减少处理资源需求。

    Matrix quantization with vector quantization error compensation and neural network postprocessing for robust speech recognition
    10.
    发明授权
    Matrix quantization with vector quantization error compensation and neural network postprocessing for robust speech recognition 有权
    矩阵量化与矢量量化误差补偿和神经网络后处理，用于鲁棒语音识别

    公开(公告)号：US06347297B1

    公开(公告)日：2002-02-12

    申请号：US09166640

    申请日：1998-10-05

    Applicant: Safdar M. Asghar ,  Lin Cong

    Inventor： Safdar M. Asghar ,  Lin Cong

    IPC: G10L1508

    CPC classification number: G10L15/02 ,  G10L15/144

    Abstract: A speech recognition system utilizes both matrix and vector quantizers as front ends to a second stage speech classifier such as hidden Markov models (HMMs) and utilizes neural network postprocessing to, for example, improve speech recognition performance. Matrix quantization exploits the “evolution” of the speech short-term spectral envelopes as well as frequency domain information, and vector quantization (VQ) primarily operates on frequency domain information. Time domain information may be substantially limited which may introduce error into the matrix quantization, and the VQ may provide error compensation. The matrix and vector quantizers may split spectral subbands to target selected frequencies for enhanced processing and may use fuzzy associations to develop fuzzy observation sequence data. A mixer provides a variety of input data to the neural network for classification determination. The neural network's ability to analyze the input data generally enhances recognition accuracy. Fuzzy operators may be utilized to reduce quantization error. Multiple codebooks may also be combined to form single respective codebooks for split matrix and split vector quantization to reduce processing resources demand.

    Abstract translation: 语音识别系统利用矩阵和矢量量化器作为第二级语音分类器的前端，例如隐马尔可夫模型（HMM），并利用神经网络后处理来改善语音识别性能。 矩阵量化利用语音短期频谱包络和频域信息的“演化”，矢量量化（VQ）主要对频域信息进行操作。 时域信息可能基本上受到限制，这可能会将错误引入到矩阵量化中，并且VQ可以提供误差补偿。 矩阵和矢量量化器可以将频谱子带分解成目标选择的频率用于增强处理，并且可以使用模糊关联来开发模糊观测序列数据。 混合器为神经网络提供各种输入数据，用于分类确定。 神经网络分析输入数据的能力通常提高了识别精度。 可以使用模糊算子来减少量化误差。 多个码本也可以组合以形成用于分割矩阵和分割矢量量化的单个相应码本，以减少处理资源需求。

Patent Agency Ranking