专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07206741B2 Method of speech recognition using time-dependent interpolation and hidden dynamic value classes 有权
标题翻译：使用时间依赖插值和隐藏动态值类的语音识别方法
公开(公告)号：US07206741B2
公开(公告)日：2007-04-17
申请号：US11294858
申请日：2005-12-06
申请人： Li Deng , Jian-lai Zhou , Frank Torsten Bernd Seide , Asela J. R. Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
发明人： Li Deng , Jian-lai Zhou , Frank Torsten Bernd Seide , Asela J. R. Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
IPC分类号： G10L15/04
CPC分类号： G10L15/12 , G10L2015/025
摘要： A speech signal is decoded by determining a production-related value for a current state based on an optimal production-related value at the end of a preceding state, the optimal production-related value being selected from a set of continuous values. The production-related value is used to determine a likelihood of a phone being represented by a set of observation vectors that are aligned with a path between the preceding state and the current state. The likelihood of the phone is combined with a score from the preceding state to determine a score for the current state, the score from the preceding state being associated with a discrete class of production-related values wherein the class matches the class of the optimal production-related value.
摘要翻译：通过基于在先前状态结束时的最佳生产相关值来确定当前状态的生产相关值来解码语音信号，从一组连续值中选择最佳生产相关值。生产相关值用于确定电话由与先前状态和当前状态之间的路径对准的一组观察向量表示的可能性。电话的可能性与来自前述状态的得分组合以确定当前状态的分数，来自前一状态的分数与生产相关值的离散类相关联，其中该类与最佳生产类别匹配相关价值。

2. 发明授权

US07050975B2 Method of speech recognition using time-dependent interpolation and hidden dynamic value classes 有权
标题翻译：使用时间依赖插值和隐藏动态值类的语音识别方法
公开(公告)号：US07050975B2
公开(公告)日：2006-05-23
申请号：US10267522
申请日：2002-10-09
申请人： Li Deng , Jian-Iai Zhou , Frank Torsten Bernd Seide , Asela J. R. Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
发明人： Li Deng , Jian-Iai Zhou , Frank Torsten Bernd Seide , Asela J. R. Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
IPC分类号： G10L15/14
CPC分类号： G10L15/12 , G10L2015/025
摘要： A method of speech recognition is provided that identifies a production-related dynamics value by performing a linear interpolation between a production-related dynamics value at a previous time and a production-related target using a time-dependent interpolation weight. The hidden production-related dynamics value is used to compute a predicted value that is compared to an observed value of acoustics to determine the likelihood of the observed acoustics given a sequence of hidden phonological units. In some embodiments, the production-related dynamics value at the previous time is selected from a set of continuous values. In addition, the likelihood of the observed acoustics given a sequence of hidden phonological units is combined with a score associated with a discrete class of production-related dynamic values at the previous time to determine a score for a current phonological state.
摘要翻译：提供了一种语音识别方法，其通过使用时间相关的内插权重在前一时间通过执行生产相关动态值与生产相关目标之间的线性插值来识别生产相关动态值。隐藏的生产相关动态值用于计算与观测值相比较的预测值，以确定给定隐藏语音单元序列的观测声学的可能性。在一些实施例中，从一组连续值中选择先前时间的生产相关动态值。另外，给出隐藏语音单元序列的观测声学的可能性与前一时刻与离散类别的生产相关动态值相关联的得分组合，以确定当前语音状态的得分。

3. 发明申请

US20060085191A1 Method of speech recognition using time-dependent interpolation and hidden dynamic value classes 有权
标题翻译：使用时间依赖插值和隐藏动态值类的语音识别方法
公开(公告)号：US20060085191A1
公开(公告)日：2006-04-20
申请号：US11294858
申请日：2005-12-06
申请人： Li Deng , Jian-Iai Zhou , Frank Seide , Asela Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
发明人： Li Deng , Jian-Iai Zhou , Frank Seide , Asela Gunawardana , Hagai Attias , Alejandro Acero , Xuedong Huang
IPC分类号： G10L15/14
CPC分类号： G10L15/12 , G10L2015/025
摘要： A speech signal is decoded by determining a production-related value for a current state based on an optimal production-related value at the end of a preceding state, the optimal production-related value being selected from a set of continuous values. The production-related value is used to determine a likelihood of a phone being represented by a set of observation vectors that are aligned with a path between the preceding state and the current state. The likelihood of the phone is combined with a score from the preceding state to determine a score for the current state, the score from the preceding state being associated with a discrete class of production-related values wherein the class matches the class of the optimal production-related value.
摘要翻译：通过基于在先前状态结束时的最佳生产相关值来确定当前状态的生产相关值来解码语音信号，从一组连续值中选择最佳生产相关值。生产相关值用于确定电话由与先前状态和当前状态之间的路径对准的一组观察向量表示的可能性。电话的可能性与来自前述状态的得分组合以确定当前状态的分数，来自前一状态的分数与生产相关值的离散类相关联，其中该类与最佳生产类别匹配相关价值。

4. 发明授权

US06990447B2 Method and apparatus for denoising and deverberation using variational inference and strong speech models 有权
公开(公告)号：US06990447B2
公开(公告)日：2006-01-24
申请号：US09999576
申请日：2001-11-15
申请人： Hagai Attias , John Carlton Platt , Li Deng , Alejandro Acero
发明人： Hagai Attias , John Carlton Platt , Li Deng , Alejandro Acero
IPC分类号： G10L15/08 , G10L15/12 , G10L15/06 , G10L21/02
CPC分类号： G10L21/0208 , G10L2021/02082 , H04R2225/43
摘要： A probability distribution for speech model parameters, such as auto-regression parameters, is used to identify a distribution of denoised values from a noisy signal. Under one embodiment, the probability distributions of the speech model parameters and the denoised values are adjusted to improve a variational inference so that the variational inference better approximates the joint probability of the speech model parameters and the denoised values given a noisy signal. In some embodiments, this improvement is performed during an expectation step in an expectation-maximization algorithm. The statistical model can also be used to identify an average spectrum for the clean signal and this average spectrum may be provided to a speech recognizer instead of the estimate of the clean signal.

5. 发明申请

US20050114134A1 Method and apparatus for continuous valued vocal tract resonance tracking using piecewise linear approximations 审中-公开
标题翻译：使用分段线性近似的连续值声道共振跟踪的方法和装置
公开(公告)号：US20050114134A1
公开(公告)日：2005-05-26
申请号：US10723995
申请日：2003-11-26
申请人： Li Deng , Hagai Attias , Alejandro Acero , Leo Lee
发明人： Li Deng , Hagai Attias , Alejandro Acero , Leo Lee
IPC分类号： G10L15/10 , G10L11/00 , G10L15/02 , G10L15/14 , G10L15/28 , G10L19/06
CPC分类号： G10L25/48 , G10L25/15
摘要： A method and apparatus tracks vocal tract resonance components, including both frequencies and bandwidths, in a speech signal. The components are tracked by defining a state equation that is linear with respect to a past vocal tract resonance vector and that predicts a current vocal tract resonance vector. An observation equation is also defined that is linear with respect to a current vocal tract resonance vector and that predicts at least one component of an observation vector. The state equation, the observation equation, and a sequence of observation vectors are used to identify a sequence of vocal tract resonance vectors using Kalman filter algorithm. Under one embodiment, the observation equation is defined based on a piecewise linear approximation to a non-linear function. The parameters of the linear approximation are selected based on pre-defined regions, which are determined from a crude estimate of a vocal tract resonance vector.
摘要翻译：一种方法和装置在语音信号中跟踪声道共振分量，包括频率和频带两者。通过定义相对于过去声道共振矢量线性的状态方程并且预测当前声道共振矢量来跟踪组件。还定义了相对于当前声道共振矢量是线性的并且预测观察矢量的至少一个分量的观察方程。状态方程，观察方程和观察矢量序列用于使用卡尔曼滤波算法识别声道共振矢量序列。在一个实施例中，基于对非线性函数的分段线性近似来定义观察方程。基于由声道共振矢量的粗略估计确定的预定义区域来选择线性近似的参数。

6. 发明授权

US07003455B1 Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech 失效
标题翻译：使用校正和缩放矢量进行噪声降低的方法，其中噪声语音领域的声学空间分割
公开(公告)号：US07003455B1
公开(公告)日：2006-02-21
申请号：US09688764
申请日：2000-10-16
申请人： Li Deng , Xuedong Huang , Alejandro Acero
发明人： Li Deng , Xuedong Huang , Alejandro Acero
IPC分类号： G10L15/20
CPC分类号： G10L21/0208
摘要： A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.
摘要翻译：提供了一种用于减少训练信号和/或测试信号中的噪声的方法和装置。噪声降低技术使用由两个信道信号形成的立体声信号，每个信道包含相同的模式信号。一个通道信号是“干净的”，另一个包括加性噪声。使用来自这些信道信号的特征向量，确定噪声校正和缩放向量的集合。当稍后接收到噪声模式信号的特征向量时，将其乘以该特征向量的最佳缩放向量，并将最佳校正向量加到乘积以产生降噪特征向量。在一个实施例中，通过为噪声特征向量选择最佳混合分量来识别最佳缩放和校正矢量。基于与每个混合物组分相关联的噪声通道特征向量的分布来选择最佳混合物组分。

7. 发明申请

US20050149325A1 Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech 有权
标题翻译：使用校正和缩放矢量进行噪声降低的方法，其中噪声语音领域的声学空间分割
公开(公告)号：US20050149325A1
公开(公告)日：2005-07-07
申请号：US11059036
申请日：2005-02-16
申请人： Li Deng , Xuedong Huang , Alejandro Acero
发明人： Li Deng , Xuedong Huang , Alejandro Acero
IPC分类号： G10L15/20 , G10L21/02 , G10L21/00
CPC分类号： G10L21/0208
摘要： A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.
摘要翻译：提供了一种用于减少训练信号和/或测试信号中的噪声的方法和装置。噪声降低技术使用由两个信道信号形成的立体声信号，每个信道包含相同的模式信号。一个通道信号是“干净的”，另一个包括加性噪声。使用来自这些信道信号的特征向量，确定噪声校正和缩放向量的集合。当稍后接收到噪声模式信号的特征向量时，将其乘以该特征向量的最佳缩放向量，并将最佳校正向量加到乘积以产生降噪特征向量。在一个实施例中，通过为噪声特征向量选择最佳混合分量来识别最佳缩放和校正矢量。基于与每个混合物组分相关联的噪声通道特征向量的分布来选择最佳混合物组分。

8. 发明申请

US20050114124A1 Method and apparatus for multi-sensory speech enhancement 有权
标题翻译：多感官语音增强的方法和装置
公开(公告)号：US20050114124A1
公开(公告)日：2005-05-26
申请号：US10724008
申请日：2003-11-26
申请人： Zicheng Liu , Michael Sinclair , Alejandro Acero , Xuedong Huang , James Droppo , Li Deng , Zhengyou Zhang , Yanli Zheng
发明人： Zicheng Liu , Michael Sinclair , Alejandro Acero , Xuedong Huang , James Droppo , Li Deng , Zhengyou Zhang , Yanli Zheng
IPC分类号： G10L21/02
CPC分类号： G10L21/0208 , G10L2021/02165
摘要： A method and system use an alternative sensor signal received from a sensor other than an air conduction microphone to estimate a clean speech value. The estimation uses either the alternative sensor signal alone, or in conjunction with the air conduction microphone signal. The clean speech value is estimated without using a model trained from noisy training data collected from an air conduction microphone. Under one embodiment, correction vectors are added to a vector formed from the alternative sensor signal in order to form a filter, which is applied to the air conductive microphone signal to produce the clean speech estimate. In other embodiments, the pitch of a speech signal is determined from the alternative sensor signal and is used to decompose an air conduction microphone signal. The decomposed signal is then used to determine a clean signal estimate.
摘要翻译：一种方法和系统使用从除空气传导麦克风以外的传感器接收的替代传感器信号来估计干净的语音值。该估计单独使用替代传感器信号，或者与导气麦克风信号一起使用。无需使用从空气传导麦克风收集的噪声训练数据训练的模型来估计干净的语音值。在一个实施例中，校正矢量被添加到由替代传感器信号形成的矢量中，以形成滤波器，该滤波器被施加到空气传导麦克风信号以产生干净的语音估计。在其他实施例中，语音信号的音调由替代传感器信号确定，并用于分解空气传导麦克风信号。然后使用分解的信号来确定干净的信号估计。

9. 发明授权

US07254536B2 Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech 有权
标题翻译：使用校正和缩放矢量进行噪声降低的方法，其中噪声语音领域的声学空间分割
公开(公告)号：US07254536B2
公开(公告)日：2007-08-07
申请号：US11059036
申请日：2005-02-16
申请人： Li Deng , Xuedong Huang , Alejandro Acero
发明人： Li Deng , Xuedong Huang , Alejandro Acero
IPC分类号： G10L21/02
CPC分类号： G10L21/0208
摘要： A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.
摘要翻译：提供了一种用于减少训练信号和/或测试信号中的噪声的方法和装置。噪声降低技术使用由两个信道信号形成的立体声信号，每个信道包含相同的模式信号。一个通道信号是“干净的”，另一个包括加性噪声。使用来自这些信道信号的特征向量，确定噪声校正和缩放向量的集合。当稍后接收到噪声模式信号的特征向量时，将其乘以该特征向量的最佳缩放向量，并将最佳校正向量加到乘积以产生降噪特征向量。在一个实施例中，通过为噪声特征向量选择最佳混合分量来识别最佳缩放和校正矢量。基于与每个混合物组分相关联的噪声通道特征向量的分布来选择最佳混合物组分。

10. 发明授权

US08700552B2 Exploiting sparseness in training deep neural networks 有权
标题翻译：在深层神经网络训练中利用稀疏性
公开(公告)号：US08700552B2
公开(公告)日：2014-04-15
申请号：US13305741
申请日：2011-11-28
申请人： Dong Yu , Li Deng , Frank Torsten Bernd Seide , Gang Li
发明人： Dong Yu , Li Deng , Frank Torsten Bernd Seide , Gang Li
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N3/08
摘要： Deep Neural Network (DNN) training technique embodiments are presented that train a DNN while exploiting the sparseness of non-zero hidden layer interconnection weight values. Generally, a fully connected DNN is initially trained by sweeping through a full training set a number of times. Then, for the most part, only the interconnections whose weight magnitudes exceed a minimum weight threshold are considered in further training. This minimum weight threshold can be established as a value that results in only a prescribed maximum number of interconnections being considered when setting interconnection weight values via an error back-propagation procedure during the training. It is noted that the continued DNN training tends to converge much faster than the initial training.
摘要翻译：提出了深层神经网络（DNN）训练技术实施例，其训练DNN，同时利用非零隐藏层互连权重值的稀疏性。通常，完全连接的DNN最初通过遍历完整的训练集多次进行训练。那么，在大多数情况下，只有重量大小超过最小重量阈值的互连在进一步的训练中被考虑。该最小权重阈值可以被建立为在训练期间通过错误反向传播过程设置互连权重值时仅考虑规定的最大数量的互连的值。值得注意的是，继续进行的DNN训练往往比初始训练快得多。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式