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

WO2013146101A1 METHOD FOR PROCESSING TEXT TO CONSTRUCT MODEL OF TEXT 审中-公开
标题翻译：用于处理文本来构建文本模型的方法
公开(公告)号：WO2013146101A1
公开(公告)日：2013-10-03
申请号：PCT/JP2013/055766
申请日：2013-02-26
申请人： MITSUBISHI ELECTRIC CORPORATION , HERSHEY, John R. , LE ROUX, Jonathan , HEAKULANI, Creighton K
发明人： HERSHEY, John R. , LE ROUX, Jonathan , HEAKULANI, Creighton K
IPC分类号： G06F17/30 , G06F17/27
CPC分类号： G06F17/30663 , G06F17/2785
摘要： Text is processed to construct a model of the text. The text has a shared vocabulary. The text is partitioned into sets and subsets of texts. The usage of the shared vocabulary in two or more sets is different, and the topics of two or more subsets are different. A probabilistic model is defined for the text. The probabilistic model considers each word in the text to be a token having a position and a word value, and the usage of the shared vocabulary, topics, subtopics, and word values for each token in the text are represented using distributions of random variables in the probabilistic model, wherein the random variables are discrete. Parameters are estimated for the model corresponding to the vocabulary usages, the word values, the topics, and the subtopics associated with the words.
摘要翻译：处理文本以构建文本的模型。该文本具有共享词汇。文本被分割成文本的集合和子集。在两个或多个集合中使用共享词汇是不同的，并且两个或多个子集的主题是不同的。为文本定义概率模型。概率模型将文本中的每个单词视为具有位置和单词值的令牌，并且使用文本中每个标记的共享词汇表，主题，子主题和单词值的使用，使用随机变量的分布来表示概率模型，其中随机变量是离散的。对于与词汇相关联的词汇用法，词汇值，主题和子主题的模型，估计参数。

2. 发明申请

WO2013111476A1 METHOD FOR ENHANCING SPEECH IN MIXED SIGNAL 审中-公开
标题翻译：用于增强混合信号中的语音的方法
公开(公告)号：WO2013111476A1
公开(公告)日：2013-08-01
申请号：PCT/JP2012/082598
申请日：2012-12-11
申请人： MITSUBISHI ELECTRIC CORPORATION , HERSHEY, John, R. , LE ROUX, Jonathan
发明人： HERSHEY, John, R. , LE ROUX, Jonathan
IPC分类号： G10L21/0232 , G10L21/02
CPC分类号： G10L21/0216 , G10L21/0232
摘要： Enhanced speech is produced from a mixed signal including noise and the speech. The noise in the mixed signal is estimated using a vector-Taylor series. The estimated noise is in terms of a minimum mean-squared error. Then, the noise is subtracted from the mixed signal to obtain the enhanced speech.
摘要翻译：增强语音由包括噪声和语音在内的混合信号产生。使用向量 - 泰勒级数来估计混合信号中的噪声。估计的噪声是最小均方误差。然后，从混合信号中减去噪声以获得增强的语音。

3. 发明申请

WO2017007035A8 METHOD FOR DISTINGUISHING ONE OR MORE COMPONENTS OF SIGNAL 审中-公开
公开(公告)号：WO2017007035A8
公开(公告)日：2017-01-12
申请号：PCT/JP2016/070355
申请日：2016-07-05
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： HERSHEY, John , LE ROUX, Jonathan , WATANABE, Shinji , CHEN, Zhuo
IPC分类号： G06N99/00 , G10L21/0272
摘要： A method distinguishes components of an acoustic 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 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.

4. 发明申请

WO2014065342A1 METHOD FOR TRANSFORMING INPUT SIGNAL 审中-公开
标题翻译：变换输入信号的方法
公开(公告)号：WO2014065342A1
公开(公告)日：2014-05-01
申请号：PCT/JP2013/078747
申请日：2013-10-17
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： HERSHEY, John, R. , FEVOTTE, Cedric , LE ROUX, Jonathan
IPC分类号： G10L21/0232 , G10L21/0216
CPC分类号： G10L21/0232 , G10L2021/02163
摘要： An input signal, in the form of a sequence of feature vectors, is transformed to an output signal by first storing parameters of a model of the input signal in a memory. Using the vectors and the parameters, a sequence of vectors of hidden variables is inferred. There is at least one vector h n of hidden variables h i,n for each feature vector x n , and each hidden variable is nonnegative. The output signal is generated using the feature vectors, the vectors of hidden variables, and the parameters. Each feature vector x n is dependent on at least one of the hidden variables h i,n for the same n . The hidden variables are related according to formula (1), where j and l are summation indices. The parameters include non-negative weights c i,j,l , and ε l,n are independent non-negative random variables.
摘要翻译：通过首先将输入信号的模型的参数存储在存储器中，以特征向量序列的形式的输入信号被变换为输出信号。使用向量和参数，推断出隐藏变量的向量序列。对于每个特征向量x n，存在隐藏变量h i，n的至少一个向量h n，并且每个隐藏变量是非负的。使用特征向量，隐藏变量的向量和参数生成输出信号。每个特征向量x n取决于相同n的隐藏变量h i，n中的至少一个。隐含变量根据公式（1）相关，其中j和l是求和指数。参数包括非负权重c i，j，l和＆egr; l，n是独立的非负随机变量。

5. 发明申请

WO2021075583A1 MANUFACTURING AUTOMATION USING ACOUSTIC SEPARATION NEURAL NETWORK 审中-公开
公开(公告)号：WO2021075583A1
公开(公告)日：2021-04-22
申请号：PCT/JP2020/039473
申请日：2020-10-14
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： WICHERN, Gordon , LE ROUX, Jonathan , PISHDADIAN, Fatemeh
IPC分类号： G05B19/406 , G05B23/02 , G07C3/00 , G06N3/04 , G06N20/00 , G06N3/08
摘要： A system for controlling an operation of a machine including a plurality of actuators assisting one or multiple tools to perform one or multiple tasks, in response to receiving an acoustic mixture of signals generated by the tool performing a task and by the plurality of actuators actuating the tool, submit the acoustic mixture of signals into a neural network trained to separate from the acoustic mixture a signal generated by the tool performing the task from signals generated by the actuators actuating the tool to extract the signal generated by the tool performing the task from the acoustic mixture of signals, analyze the extracted signal to produce a state of performance of the task, and execute a control action selected according to the state of performance of the task.

6. 发明申请

WO2020195068A1 SYSTEM AND METHOD FOR END-TO-END SPEECH RECOGNITION WITH TRIGGERED ATTENTION 审中-公开
公开(公告)号：WO2020195068A1
公开(公告)日：2020-10-01
申请号：PCT/JP2020/002201
申请日：2020-01-16
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： MORITZ, Niko , HORI, Takaaki , LE ROUX, Jonathan
IPC分类号： G10L15/16 , G06N3/04 , G10L15/32
摘要： A speech recognition system includes an encoder to convert an input acoustic signal into a sequence of encoder states, an alignment decoder to identify locations of encoder states in the sequence of encoder states that encode transcription outputs, a partition module to partition the sequence of encoder states into a set of partitions based on the locations of the identified encoder states, and an attention-based decoder to determine the transcription outputs for each partition of encoder states submitted to the attention-based decoder as an input. Upon receiving the acoustic signal, the system uses the encoder to produce the sequence of encoder states, partitions the sequence of encoder states into the set of partitions based on the locations of the encoder states identified by the alignment decoder, and submits the set of partitions sequentially into the attention-based decoder to produce a transcription output for each of the submitted partitions.

7. 发明申请

WO2019198265A1 SPEECH RECOGNITION SYSTEM AND METHOD USING SPEECH RECOGNITION SYSTEM 审中-公开
公开(公告)号：WO2019198265A1
公开(公告)日：2019-10-17
申请号：PCT/JP2018/040422
申请日：2018-10-24
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： LE ROUX, Jonathan , HORI, Takaaki , SETTLE, Shane , SEKI, Hiroshi , WATANABE, Shinji , HERSHEY, John
IPC分类号： G10L25/30
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.

8. 发明申请

WO2016063794A1 METHOD FOR TRANSFORMING A NOISY AUDIO SIGNAL TO AN ENHANCED AUDIO SIGNAL 审中-公开
标题翻译：将噪声音频信号转换为增强音频信号的方法
公开(公告)号：WO2016063794A1
公开(公告)日：2016-04-28
申请号：PCT/JP2015/079241
申请日：2015-10-08
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： ERDOGAN, Hakan , HERSHEY, John , WATANABE, Shinji , LE ROUX, Jonathan
IPC分类号： G10L25/30 , G10L21/0208 , G10L21/0324 , G06N3/02
CPC分类号： G10L21/0208 , G10L21/0216 , G10L21/0324 , G10L25/03 , G10L25/30
摘要： A method transforms a noisy audio signal to an enhanced audio signal, by first acquiring the noisy audio signal from an environment. The noisy audio signal is processed by an enhancement network having network parameters to jointly produce a magnitude mask and a phase estimate. Then, the magnitude mask and the phase estimate are used to obtain the enhanced audio signal.
摘要翻译：通过首先从环境获取噪声音频信号，方法将噪声音频信号转换为增强音频信号。噪声音频信号由具有网络参数的增强网络处理，以共同产生幅度掩模和相位估计。然后，使用幅度掩模和相位估计来获得增强音频信号。

9. 发明申请

WO2023276251A1 ARTIFICIAL INTELLIGENCE SYSTEM FOR SEQUENCE-TO-SEQUENCE PROCESSING WITH DUAL CAUSAL AND NON-CAUSAL RESTRICTED SELF-ATTENTION ADAPTED FOR STREAMING APPLICATIONS 审中-公开
公开(公告)号：WO2023276251A1
公开(公告)日：2023-01-05
申请号：PCT/JP2022/006283
申请日：2022-02-04
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： MORITZ, Niko , HORI, Takaaki , LE ROUX, Jonathan
IPC分类号： G06N3/04 , G10L15/16 , G06N3/08
摘要： The present disclosure provides an artificial intelligence (AI) system for sequence-to-sequence modeling with attention adapted for streaming applications. The AI system comprises at least one processor; and memory having instructions stored thereon that, when executed by the processor, cause the AI system to process each input frame in a sequence of input frames through layers of a deep neural network (DNN) to produce a sequence of outputs. At least some of the layers of the DNN include a dual self-attention module having a dual non-causal and causal architecture attending to non-causal frames and causal frames. Further, the AI system renders the sequence of outputs.

10. 发明申请

WO2022085250A1 TRAINING A NEURAL NETWORK USING GRAPH-BASED TEMPORAL CLASSIFICATION 审中-公开
公开(公告)号：WO2022085250A1
公开(公告)日：2022-04-28
申请号：PCT/JP2021/025874
申请日：2021-07-02
申请人： MITSUBISHI ELECTRIC CORPORATION
发明人： MORITZ, Niko , HORI, Takaaki , LE ROUX, Jonathan
IPC分类号： G06N3/08
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.

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