Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Corporation

Shinji Watanabe

John R Hershey

Jonathan Le Roux

Takaaki Hori

Chiori Hori

Bret Harsham

Zhuo Chen

Hiroshi Seki

Gordon P Wichern

Hakan Erdogan

Felix Weninger

Yi Luan

Yuki Tachioka

Hao Tang

Shane Settle

Tsubasa Ochiai

John Hershey

A speech recognition system includes a plurality of microphones to receive acoustic signals including speech signals, an input interface to generate multichannel inputs from the acoustic signals, one or more storages to store a multichannel speech recognition network, wherein the multichannel speech recognition network comprises mask estimation networks to generate time-frequency masks from the multichannel inputs, a beamformer network trained to select a reference channel input from the multichannel inputs using the time-frequency masks and generate an enhanced speech dataset based on the reference channel input and an encoder-decoder network trained to transform the enhanced speech dataset into a text. The system further includes one or more processors, using the multichannel speech recognition network in association with the one or more storages, to generate the text from the multichannel inputs, and an output interface to render the text.

System and method for multichannel end-to-end speech recognition

A method for performing multi-label classification includes extracting a feature vector from an input vector including input data by a feature extractor, determining, by a label predictor, a relevant vector including relevant labels having relevant scores based on the feature vector, updating a binary masking vector by masking pre-selected labels having been selected in previous label selections, applying the updated binary masking vector to the relevant vector such that the relevant label vector is updated to exclude the pre-selected labels from the relevant labels, and selecting a relevant label from the updated relevant label vector based on the relevant scores of the updated relevant label vector.

Method and system for multi-label classification

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.

Methods and systems for recognizing simultaneous speech by multiple speakers

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.

Methods and systems for enhancing audio signals corrupted by noise

A speech recognition system includes an input device to receive voice sounds, one or more processors, and one or more storage devices storing parameters and program modules including instructions which cause the one or more processors to perform operations. The operations include extracting an acoustic feature sequence from audio waveform data converted from the voice sounds, encoding the acoustic feature sequence into a hidden vector sequence using an encoder network having encoder network parameters, predicting first output label sequence probabilities by feeding the hidden vector sequence to a decoder network having decoder network parameters, predicting second output level sequence probabilities by a hybrid network using character-base language models (LMs) and word-level LMs; and searching, using a label sequence search module, for an output label sequence having a highest sequence probability by combining the first and second output label sequence probabilities provided from the decoder network and the hybrid network.

Method and apparatus for open-vocabulary end-to-end speech recognition

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.

Method and apparatus for multi-lingual end-to-end speech recognition

A method and for training a language model to reduce recognition errors, wherein the language model is a recurrent neural network language model (RNNLM) by first acquiring training samples. An automatic speech recognition system (ASR) is applied to the training samples to produce recognized words and probabilites of the recognized words, and an N-best list is selected from the recognized words based on the probabilities. determining word errors using reference data for hypotheses in the N-best list. The hypotheses are rescored using the RNNLM. Then, we determine gradients for the hypotheses using the word errors and gradients for words in the hypotheses. Lastly, parameters of the RNNLM are updated using a sum of the gradients.

Method and system for training language models to reduce recognition errors

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.

Method for enhancing audio signal using phase information

A method and system processes utterances that are acquired either from an automatic speech recognition (ASR) system or text. The utterances have associated identities of each party, such as role A utterances and role B utterances. The information corresponding to utterances, such as word sequence and identity, are converted to features. Each feature is received in an input layer of a neural network (NN). A dimensionality of each feature is reduced, in a projection layer of the NN, to produce a reduced dimensional feature. The reduced dimensional feature is processed to provide probabilities of labels for the utterances.

Method and system for role dependent context sensitive spoken and textual language understanding with neural networks

A method for processing a voice command using a statistical dialog model determines a belief state as a probability distribution over states organized in a hierarchy with a parent-child relationship of nodes representing the states. The belief state includes the hierarchy of state variables defining probabilities of each state to correspond to the voice command and a probability of a state of a child node in the hierarchy is conditioned on a probability of a state of a corresponding parent node. A system action is selected based on the belief state.

Statistical voice dialog system and method

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.

Method for distinguishing components of signal of environment

A method estimates source signals from a mixture of source signals by first training an analysis model and a reconstruction model using training data. The analysis model is applied to the mixture of source signals to obtain an analysis representation of the mixture of source signals, and the reconstruction model is applied to the analysis representation to obtain an estimate of the source signals, wherein the analysis model utilizes an analysis linear basis representation, and the reconstruction model utilizes a reconstruction linear basis representation.

Source signal separation by discriminatively-trained non-negative matrix factorization

A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.

Method for using a multi-scale recurrent neural network with pretraining for spoken language understanding tasks

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.

Method for processing speech signals using an ensemble of speech enhancement procedures

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.

Growing community of inventors

Arlington, MA, United States of America

Shinji Watanabe