公开(公告)号：US20120254086A1

公开(公告)日：2012-10-04

申请号：US13077978

申请日：2011-03-31

申请人： Li Deng ,  Dong Yu ,  Alejandro Acero

发明人： Li Deng ,  Dong Yu ,  Alejandro Acero

IPC分类号： G06N3/08

CPC分类号： G06N3/08 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454

摘要： A method is disclosed herein that includes an act of causing a processor to access a deep-structured, layered or hierarchical model, called deep convex network, retained in a computer-readable medium, wherein the deep-structured model comprises a plurality of layers with weights assigned thereto. This layered model can produce the output serving as the scores to combine with transition probabilities between states in a hidden Markov model and language model scores to form a full speech recognizer. The method makes joint use of nonlinear random projections and RBM weights, and it stacks a lower module's output with the raw data to establish its immediately higher module. Batch-based, convex optimization is performed to learn a portion of the deep convex network's weights, rendering it appropriate for parallel computation to accomplish the training. The method can further include the act of jointly substantially optimizing the weights, the transition probabilities, and the language model scores of the deep-structured model using the optimization criterion based on a sequence rather than a set of unrelated frames.

摘要翻译： 本文公开了一种方法，其包括使处理器访问被保留在计算机可读介质中的称为深凸网络的深层结构的分层或层次模型的动作，其中深层结构模型包括多个具有 分配给它的权重。 该分层模型可以产生作为分数的输出，以与隐藏的马尔可夫模型和语言模型分数中的状态之间的转移概率相结合，以形成完整的语音识别器。 该方法联合使用非线性随机投影和RBM权重，并将较低模块的输出与原始数据叠加以建立其立即更高的模块。 执行基于批次的凸优化来学习深凸网络权重的一部分，使其适合于并行计算以完成训练。 该方法还可以包括使用基于序列而不是一组不相关帧的优化准则共同基本优化深层结构模型的权重，转移概率和语言模型分数的动作。

公开(公告)号：US08185389B2

公开(公告)日：2012-05-22

申请号：US12335558

申请日：2008-12-16

申请人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Jian Wu ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Jian Wu ,  Alejandro Acero

IPC分类号： G10L15/20

CPC分类号： G10L21/0208 ,  G10L15/20

摘要： Described is noise reduction technology generally for speech input in which a noise-suppression related gain value for the frame is determined based upon a noise level associated with that frame in addition to the signal to noise ratios (SNRs). In one implementation, a noise reduction mechanism is based upon minimum mean square error, Mel-frequency cepstra noise reduction technology. A high gain value (e.g., one) is set to accomplish little or no noise suppression when the noise level is below a threshold low level, and a low gain value set or computed to accomplish large noise suppression above a threshold high noise level. A noise-power dependent function, e.g., a log-linear interpolation, is used to compute the gain between the thresholds. Smoothing may be performed by modifying the gain value based upon a prior frame's gain value. Also described is learning parameters used in noise reduction via a step-adaptive discriminative learning algorithm.

摘要翻译： 描述了通常用于语音输入的噪声降低技术，其中除了信噪比（SNR）之外，基于与该帧相关联的噪声电平来确定用于帧的噪声抑制相关增益值。 在一个实现中，降噪机制基于最小均方误差，Mel-frequency cepstra降噪技术。 设置高增益值（例如一个），以在噪声电平低于阈值低电平时实现很少或没有噪声抑制，以及设置或计算的低增益值，以实现高于阈值高噪声电平的大噪声抑制。 使用噪声功率相关函数，例如对数线性插值来计算阈值之间的增益。 可以通过基于先前帧的增益值修改增益值来执行平滑化。 还描述了通过步进自适应识别学习算法在降噪中使用的学习参数。

公开(公告)号：US07856351B2

公开(公告)日：2010-12-21

申请号：US11655703

申请日：2007-01-19

申请人： Sibel Yaman ,  Li Deng ,  Dong Yu ,  Ye-Yi Wang ,  Alejandro Acero

发明人： Sibel Yaman ,  Li Deng ,  Dong Yu ,  Ye-Yi Wang ,  Alejandro Acero

IPC分类号： G06F17/27

CPC分类号： G10L15/1815

摘要： A novel system integrates speech recognition and semantic classification, so that acoustic scores in a speech recognizer that accepts spoken utterances may be taken into account when training both language models and semantic classification models. For example, a joint association score may be defined that is indicative of a correspondence of a semantic class and a word sequence for an acoustic signal. The joint association score may incorporate parameters such as weighting parameters for signal-to-class modeling of the acoustic signal, language model parameters and scores, and acoustic model parameters and scores. The parameters may be revised to raise the joint association score of a target word sequence with a target semantic class relative to the joint association score of a competitor word sequence with the target semantic class. The parameters may be designed so that the semantic classification errors in the training data are minimized.

摘要翻译： 一种新颖的系统集成了语音识别和语义分类，从而在训练语言模型和语义分类模型时，可以考虑接受讲话语音的语音识别器中的声学分数。 例如，可以定义联合关联分数，其表示声学信号的语义类别和单词序列的对应关系。 联合关联分数可以包括参数，例如声信号的信号到类建模的加权参数，语言模型参数和分数，以及声学模型参数和分数。 可以修改参数以相对于具有目标语义类的竞争者词序列的联合关联分数来提高具有目标语义类别的目标词序列的联合关联分数。 可以设计参数，使得训练数据中的语义分类误差最小化。

公开(公告)号：US20100256977A1

公开(公告)日：2010-10-07

申请号：US12416161

申请日：2009-04-01

申请人： Dong Yu ,  Li Deng ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Alejandro Acero

IPC分类号： G10L15/00

CPC分类号： G10L15/14 ,  G06K9/6277 ,  G06K9/6297

摘要： Described is a technology by which a maximum entropy (MaxEnt) model, such as used as a classifier or in a conditional random field or hidden conditional random field that embed the maximum entropy model, uses continuous features with continuous weights that are continuous functions of the feature values (instead of single-valued weights). The continuous weights may be approximated by a spline-based solution. In general, this converts the optimization problem into a standard log-linear optimization problem without continuous weights at a higher-dimensional space.

摘要翻译： 描述了最大熵（MaxEnt）模型，例如用作分类器或嵌入最大熵模型的条件随机场或隐藏条件随机场的最大熵（MaxEnt）模型使用具有连续权重的连续特征，连续权重是连续权重， 特征值（而不是单值权重）。 连续权重可以通过基于样条的解决方案近似。 一般来说，这将优化问题转化为标准的对数线性优化问题，而在较高维度的空间则没有连续权重。

公开(公告)号：US20100076758A1

公开(公告)日：2010-03-25

申请号：US12236530

申请日：2008-09-24

申请人： Jinyu Li ,  Li Deng ,  Dong Yu ,  Yifan Gong ,  Alejandro Acero

发明人： Jinyu Li ,  Li Deng ,  Dong Yu ,  Yifan Gong ,  Alejandro Acero

IPC分类号： G10L15/20 ,  G10L15/14

CPC分类号： G10L15/065 ,  G10L15/20

摘要： A speech recognition system described herein includes a receiver component that receives a distorted speech utterance. The speech recognition also includes an updater component that is in communication with a first model and a second model, wherein the updater component automatically updates parameters of the second model based at least in part upon joint estimates of additive and convolutive distortions output by the first model, wherein the joint estimates of additive and convolutive distortions are estimates of distortions based on a phase-sensitive model in the speech utterance received by the receiver component. Further, distortions other than additive and convolutive distortions, including other stationary and nonstationary sources, can also be estimated used to update the parameters of the second model.

摘要翻译： 本文描述的语音识别系统包括接收失真的语音话语的接收机组件。 所述语音识别还包括与第一模型和第二模型通信的更新器组件，其中所述更新器组件至少部分地基于由所述第一模型输出的加法和卷积失真的联合估计来自动更新所述第二模型的参数 其中，加法和卷积失真的联合估计是基于由接收器部件接收的语音发声中的相敏模型的失真估计。 此外，还可以估计用于更新第二模型参数的除加法和卷积失真之外的失真，包括其他静止和非平稳源。

公开(公告)号：US20100070280A1

公开(公告)日：2010-03-18

申请号：US12211115

申请日：2008-09-16

申请人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

发明人： Dong Yu ,  Li Deng ,  Yifan Gong ,  Alejandro Acero

IPC分类号： G10L15/14

CPC分类号： G10L15/142

摘要： A speech recognition system uses Gaussian mixture variable-parameter hidden Markov models (VPHMMs) to recognize speech. The VPHMMs include Gaussian parameters that vary as a function of at least one environmental conditioning parameter. The relationship of each Gaussian parameter to the environmental conditioning parameter(s) is modeled using a piecewise fitting approach, such as by using spline functions. In a training phase, the recognition system can use clustering to identify classes of spline functions, each class grouping together spline functions which are similar to each other based on some distance measure. The recognition system can then store sets of spline parameters that represent respective classes of spline functions. An instance of a spline function that belongs to a class can make reference to an associated shared set of spline parameters. The Gaussian parameters can be represented in an efficient form that accommodates the use of sharing in the above-summarized manner.

摘要翻译： 语音识别系统使用高斯混合可变参数隐马尔可夫模型（VPHMM）来识别语音。 VPHMM包括作为至少一个环境调节参数的函数而变化的高斯参数。 每个高斯参数与环境条件参数的关系使用分段拟合方法建模，例如通过使用样条函数。 在训练阶段，识别系统可以使用聚类来识别样条函数的类别，每个类别根据一些距离度量将彼此相似的样条函数分组在一起。 识别系统然后可以存储表示各种样条函数的样条参数集合。 属于类的样条函数的一个实例可以引用相关联的一组样条参数。 高斯参数可以以适合以上述方式共享使用的有效形式来表示。

公开(公告)号：US07409346B2

公开(公告)日：2008-08-05

申请号：US11069474

申请日：2005-03-01

申请人： Alejandro Acero ,  Dong Yu ,  Li Deng

发明人： Alejandro Acero ,  Dong Yu ,  Li Deng

IPC分类号： G10L15/10

CPC分类号： G10L15/02 ,  G10L25/15 ,  G10L25/24 ,  G10L2015/025

摘要： A structured generative model of a speech coarticulation and reduction is described with a novel two-stage implementation. At the first stage, the dynamics of formants or vocal tract resonance (VTR) are generated using prior information of resonance targets in the phone sequence. Bi-directional temporal filtering with finite impulse response (FIR) is applied to the segmental target sequence as the FIR filter's input. At the second stage the dynamics of speech cepstra are predicted analytically based on the FIR filtered VTR targets. The combined system of these two stages thus generates correlated and causally related VTR and cepstral dynamics where phonetic reduction is represented explicitly in the hidden resonance space and implicitly in the observed cepstral space. The combined system also gives the acoustic observation probability given a phone sequence. Using this probability, different phone sequences can be compared and ranked in terms of their respective probability values. This then permits the use of the model for phonetic recognition.

摘要翻译： 用新的两阶段实现来描述语音合成和简化的结构化生成模型。 在第一阶段，使用电话序列中共振目标的先前信息产生共振峰或声道共振（VTR）的动力学。 具有有限脉冲响应（FIR）的双向时间滤波作为FIR滤波器的输入应用于分段目标序列。 在第二阶段，基于FIR滤波的VTR目标，分析地预测语音cepstra的动力学。 这两个阶段的组合系统因此产生相关和因果相关的VTR和倒谱动力学，其中语音减少在隐藏共振空间中明确表示，并且隐含地在观察到的倒频谱空间中。 组合系统还给出了电话序列的声学观察概率。 使用这种概率，可以根据它们各自的概率值对不同的电话序列进行比较和排序。 这样就允许使用模型进行语音识别。

公开(公告)号：US20080177547A1

公开(公告)日：2008-07-24

申请号：US11655703

申请日：2007-01-19

申请人： Sibel Yaman ,  Li Deng ,  Dong Yu ,  Ye-Yi Wang ,  Alejandro Acero

发明人： Sibel Yaman ,  Li Deng ,  Dong Yu ,  Ye-Yi Wang ,  Alejandro Acero

IPC分类号： G10L15/18

CPC分类号： G10L15/1815

摘要： A novel system integrates speech recognition and semantic classification, so that acoustic scores in a speech recognizer that accepts spoken utterances may be taken into account when training both language models and semantic classification models. For example, a joint association score may be defined that is indicative of a correspondence of a semantic class and a word sequence for an acoustic signal. The joint association score may incorporate parameters such as weighting parameters for signal-to-class modeling of the acoustic signal, language model parameters and scores, and acoustic model parameters and scores. The parameters may be revised to raise the joint association score of a target word sequence with a target semantic class relative to the joint association score of a competitor word sequence with the target semantic class. The parameters may be designed so that the semantic classification errors in the training data are minimized.

摘要翻译： 一种新颖的系统集成了语音识别和语义分类，从而在训练语言模型和语义分类模型时，可以考虑接受讲话语音的语音识别器中的声学分数。 例如，可以定义联合关联分数，其表示声学信号的语义类别和单词序列的对应关系。 联合关联分数可以包括参数，例如声信号的信号到类建模的加权参数，语言模型参数和分数，以及声学模型参数和分数。 可以修改参数以相对于具有目标语义类的竞争者词序列的联合关联分数来提高具有目标语义类别的目标词序列的联合关联分数。 可以设计参数，使得训练数据中的语义分类误差最小化。

公开(公告)号：US20060100862A1

公开(公告)日：2006-05-11

申请号：US11071904

申请日：2005-03-01

申请人： Li Deng ,  Alejandro Acero ,  Dong Yu ,  Xiang Li

发明人： Li Deng ,  Alejandro Acero ,  Dong Yu ,  Xiang Li

IPC分类号： G10L11/04

CPC分类号： G10L15/02 ,  G10L2015/025

摘要： A method of producing at least one possible sequence of vocal tract resonance (VTR) for a fixed sequence of phonetic units, and producing the acoustic observation probability by integrating over such distributions is provided. The method includes identifying a sequence of target distributions for a VTR sequence corresponding to a phone sequence with a given segmentation. The sequence of target distributions is applied to a finite impulse response filter to produce distributions for possible VTR trajectories. Then these distributions are applied to a linearized nonlinear function to produce the acoustic observation probability for the given sequence of phonetic units. This acoustic observation probability is used for phonetic recognition.

公开(公告)号：US08942978B2

公开(公告)日：2015-01-27

申请号：US13182971

申请日：2011-07-14

申请人： Li Deng ,  Dong Yu ,  Xiaolong Li ,  Alejandro Acero

发明人： Li Deng ,  Dong Yu ,  Xiaolong Li ,  Alejandro Acero

IPC分类号： G10L15/00 ,  G10L15/06

CPC分类号： G10L15/063 ,  G10L2015/025

摘要： Parameters for distributions of a hidden trajectory model including means and variances are estimated using an acoustic likelihood function for observation vectors as an objection function for optimization. The estimation includes only acoustic data and not any intermediate estimate on hidden dynamic variables. Gradient ascent methods can be developed for optimizing the acoustic likelihood function.

摘要翻译： 使用用于观察向量的声学似然函数作为优化的反对函数来估计包括装置和方差的隐藏轨迹模型的分布参数。 该估计仅包括声学数据，而不包括对隐藏的动态变量的任何中间估计。 可以开发梯度上升方法来优化声似然函数。