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. 发明申请

US20230042468A1 Method and System for Dereverberation of Speech Signals 有权
公开(公告)号：US20230042468A1
公开(公告)日：2023-02-09
申请号：US17654302
申请日：2022-03-10
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Zhong-Qiu Wang , Gordon Wichern , Jonathan Le Roux
IPC分类号： G10L21/0224 , G10L21/0232 , G10L21/0264 , G10L25/30 , G06N3/04
摘要： A system and method for reverberation reduction is disclosed. A first Deep Neural Network (DNN) produces a first estimate of a target direct-path signal from a mixture of acoustic signals that include the target direct-path signal and a reverberation of the target direct-path signal. A filter modeling a room impulse response (RIR) for the first estimate is estimated. The filter when applied to the first estimate of the target direct-path signal generates a result closest to a residual between the mixture of the acoustic signals and the first estimate of the target direct-path signal according to a distance function. A mixture with reduced reverberation of the target direct-path signal is obtained by removing the result of applying the filter to the first estimate of the target direct-path signal from the received mixture. A second DNN produces a second estimate of the target direct-path signal from the mixture with reduced reverberation.

2. 发明授权

US11475908B2 System and method for hierarchical audio source separation 有权
公开(公告)号：US11475908B2
公开(公告)日：2022-10-18
申请号：US17065322
申请日：2020-10-07
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Gordon Wichern , Jonathan Le Roux , Ethan Manilow
IPC分类号： H04R29/00 , G10L21/028 , G10L25/30 , G10L25/24 , G10L25/51 , G10L25/18 , G06F3/16
摘要： The audio processing system includes a memory to store a neural network trained to process an audio mixture to output estimation of at least a subset of a set of audio sources present in the audio mixture. The audio sources are subject to hierarchical constraints enforcing a parent-children hierarchy on the set of audio sources, such that a parent audio source in includes a mixture of its one or multiple children audio sources. The subset includes a parent audio source and at least one of its children audio sources. The system further comprises a processor to process a received input audio mixture using the neural network to estimate the subset of audio sources and their mutual relationships according to the parent-children hierarchy. The system further includes an output interface configured to render the extracted audio sources and their mutual relationships.

3. 发明申请

US20220129749A1 Training a Neural Network using Graph-Based Temporal Classification 有权
公开(公告)号：US20220129749A1
公开(公告)日：2022-04-28
申请号：US17235074
申请日：2021-04-20
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Niko Moritz , Takaaki Hori , Jonathan Le Roux
IPC分类号： G06N3/08 , G06N3/04
摘要： A method for training a neural network with a graph-based temporal classification (GTC) objective function, using a directed graph of nodes connected by edges representing labels and transitions among the labels, is provided. The directed graph specifies one or a combination of non-monotonic alignment between a sequence of labels and a sequence of probability distributions and constraints on the label repetitions. The method comprises executing a neural network to transform a sequence of observations into the sequence of probability distributions, and updating parameters of the neural network based on the GTC objective function configured to maximize a sum of conditional probabilities of all possible sequences of labels that are generated by unfolding the directed graph to the length of the sequence of observations and mapping each unfolded sequence of nodes and edges to a possible sequence of labels.

4. 发明授权

US10811000B2 Methods and systems for recognizing simultaneous speech by multiple speakers 有权
公开(公告)号：US10811000B2
公开(公告)日：2020-10-20
申请号：US15952330
申请日：2018-04-13
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Jonathan Le Roux , Takaaki Hori , Shane Settle , Hiroshi Seki , Shinji Watanabe , John Hershey
IPC分类号： G10L15/00 , G10L15/16 , G10L15/06 , G10L15/22 , G10L17/00
摘要： Systems and methods for a speech recognition system for recognizing speech including overlapping speech by multiple speakers. The system including a hardware processor. A computer storage memory to store data along with having computer-executable instructions stored thereon that, when executed by the processor is to implement a stored speech recognition network. An input interface to receive an acoustic signal, the received acoustic signal including a mixture of speech signals by multiple speakers, wherein the multiple speakers include target speakers. An encoder network and a decoder network of the stored speech recognition network are trained to transform the received acoustic signal into a text for each target speaker. Such that the encoder network outputs a set of recognition encodings, and the decoder network uses the set of recognition encodings to output the text for each target speaker. An output interface to transmit the text for each target speaker.

5. 发明授权

US10726856B2 Methods and systems for enhancing audio signals corrupted by noise 有权
公开(公告)号：US10726856B2
公开(公告)日：2020-07-28
申请号：US15998765
申请日：2018-08-16
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Jonathan Le Roux , Shinji Watanabe , John Hershey , Gordon Wichern
IPC分类号： G10L21/02 , G10L19/032 , G10L21/0272 , G10L19/00
摘要： Systems and methods for audio signal processing including an input interface to receive a noisy audio signal including a mixture of target audio signal and noise. An encoder to map each time-frequency bin of the noisy audio signal to one or more phase-related value from one or more phase quantization codebook of phase-related values indicative of the phase of the target signal. Calculate, for each time-frequency bin of the noisy audio signal, a magnitude ratio value indicative of a ratio of a magnitude of the target audio signal to a magnitude of the noisy audio signal. A filter to cancel the noise from the noisy audio signal based on the phase-related values and the magnitude ratio values to produce an enhanced audio signal. An output interface to output the enhanced audio signal.

6. 发明授权

US10593321B2 Method and apparatus for multi-lingual end-to-end speech recognition 有权
公开(公告)号：US10593321B2
公开(公告)日：2020-03-17
申请号：US15843047
申请日：2017-12-15
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Shinji Watanabe , Takaaki Hori , Hiroshi Seki , Jonathan Le Roux , John Hershey
IPC分类号： G10L15/06 , G06N3/08 , G06N7/00 , G06N3/04 , G10L15/02 , G10L15/16 , G10L15/197 , G10L15/22 , G10L15/00
摘要： A method for training a multi-language speech recognition network includes providing utterance datasets corresponding to predetermined languages, inserting language identification (ID) labels into the utterance datasets, wherein each of the utterance datasets is labelled by each of the language ID labels, concatenating the labeled utterance datasets, generating initial network parameters from the utterance datasets, selecting the initial network parameters according to a predetermined sequence, and training, iteratively, an end-to-end network with a series of the selected initial network parameters and the concatenated labeled utterance datasets until a training result reaches a threshold.

7. 发明申请

US20200058314A1 Methods and systems for enhancing audio signals corrupted by noise 审中-公开
公开(公告)号：US20200058314A1
公开(公告)日：2020-02-20
申请号：US15998765
申请日：2018-08-16
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Jonathan Le Roux , Shinji Watanabe , John Hershey , Gordon Wichem
IPC分类号： G10L19/032
摘要： Systems and methods for audio signal processing including an input interface to receive a noisy audio signal including a mixture of target audio signal and noise. An encoder to map each time-frequency bin of the noisy audio signal to one or more phase-related value from one or more phase quantization codebook of phase-related values indicative of the phase of the target signal. Calculate, for each time-frequency bin of the noisy audio signal, a magnitude ratio value indicative of a ratio of a magnitude of the target audio signal to a magnitude of the noisy audio signal. A filter to cancel the noise from the noisy audio signal based on the phase-related values and the magnitude ratio values to produce an enhanced audio signal. An output interface to output the enhanced audio signal.

8. 发明授权

US09685155B2 Method for distinguishing components of signal of environment 有权
公开(公告)号：US09685155B2
公开(公告)日：2017-06-20
申请号：US15147382
申请日：2016-05-05
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： John Hershey , Jonathan Le Roux , Shinji Watanabe , Zhuo Chen
IPC分类号： G10L15/00 , G10L15/16 , G10L25/51 , G10L25/30 , G10H1/00 , G10L21/0272 , G06N3/04 , G10L15/02 , G10L15/06 , G06K9/62
CPC分类号： G10L15/16 , G06K9/6218 , G06K9/6223 , G06K9/66 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G10H1/00 , G10H2210/056 , G10H2240/075 , G10H2250/311 , G10L15/02 , G10L15/063 , G10L21/0272 , G10L25/30 , G10L25/51
摘要： A method distinguishes components of a signal by processing the signal to estimate a set of analysis features, wherein each analysis feature defines an element of the signal and has feature values that represent parts of the signal, processing the signal to estimate input features of the signal, and processing the input features using a deep neural network to assign an associative descriptor to each element of the signal, wherein a degree of similarity between the associative descriptors of different elements is related to a degree to which the parts of the signal represented by the elements belong to a single component of the signal. The similarities between associative descriptors are processed to estimate correspondences between the elements of the signal and the components in the signal. Then, the signal is processed using the correspondences to distinguish component parts of the signal.

9. 发明申请

US20150112670A1 Denoising Noisy Speech Signals using Probabilistic Model 审中-公开
标题翻译：使用概率模型去噪嘈杂的语音信号
公开(公告)号：US20150112670A1
公开(公告)日：2015-04-23
申请号：US14225870
申请日：2014-03-26
申请人： MITSUBISHI ELECTRIC RESEARCH LABORATORIES, INC.
发明人： Jonathan Le Roux , John R. Hershey , Umut Simsekli
IPC分类号： G10L21/0208
CPC分类号： G10L21/0208 , G10L2021/02087
摘要： A method determines from an input noisy signal sequences of hidden variables including at least one sequence of hidden variables representing an excitation component of the clean speech signal, at least one sequence of hidden variables representing a filter component of the clean speech signal, and at least one sequence of hidden variables representing the noise signal. The sequences of hidden variables include hidden variables determined as a non-negative linear combination of non-negative basis functions. The determination uses the model of the clean speech signal that includes a non-negative source-filter dynamical system (NSFDS) constraining the hidden variables representing the excitation and the filter components to be statistically dependent over time. The method generates an output signal using a product of corresponding hidden variables representing the excitation and the filter components.
摘要翻译：一种方法从输入的噪声信号序列确定隐含变量，包括表示清洁语音信号的激励分量的至少一个隐藏变量序列，表示清洁语音信号的滤波器分量的至少一个隐藏变量序列，并且至少表示噪声信号的一系列隐藏变量。隐藏变量的序列包括被确定为非负基函数的非负线性组合的隐含变量。该确定使用包括非负源滤波器动力系统（NSFDS）的干净语音信号的模型，其限制表示激励的隐藏变量和滤波器分量随时间而统计依赖。该方法使用表示激励和滤波器组件的相应隐藏变量的乘积来生成输出信号。

10. 发明申请

US20150025880A1 Method for Processing Speech Signals Using an Ensemble of Speech Enhancement Procedures 有权
标题翻译：使用语音增强程序集合处理语音信号的方法
公开(公告)号：US20150025880A1
公开(公告)日：2015-01-22
申请号：US13945469
申请日：2013-07-18
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Jonathan Le Roux , Shinji Watanabe , John R. Hershey
IPC分类号： G10L21/0232 , G10L15/06
CPC分类号： G10L21/0232 , G10L15/063 , G10L21/02 , G10L21/0208 , G10L21/0272 , G10L25/78 , G10L2021/02163
摘要： A method processes an acoustic signal that is a mixture of a target signal and interfering signals by first enhancing the acoustic signal by a set of enhancement procedures to produce a set of initial enhanced signals. Then, an ensemble learning procedure is applied to the acoustic signal and the set of initial enhancement signals to produce features of the acoustic signal.
摘要翻译：一种方法通过首先通过一组增强过程增强声信号来处理作为目标信号和干扰信号的混合的声信号，以产生一组初始增强信号。然后，将整体学习过程应用于声信号和一组初始增强信号以产生声信号的特征。

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