Google Inc.

International Business Machines Corporation

Nuance Communications, Inc.

Tara N Sainath

Dimitri Kanevsky

Sasha P Caskey

Bo Li

Rohit Prakash Prabhavalkar

Ron J Weiss

Ruoming Pang

Trevor D Strohman

Bhuvana Ramabhadran

Sara H Basson

Kevin William Wilson

David Nahamoo

Yonghui Wu

Michiel A U Bacchiani

Arun Narayanan

Ehsan Variani

Sameer Maskey

Zhifeng Chen

Aleksandr Y Aravkin

Chung-Cheng Chiu

Patrick An Phu Nguyen

Yanzhang He

James R Kozloski

Peter Kenneth Malkin

Golan Pundak

David Rybach

Ke Hu

Clifford A Pickover

Robert G Farrell

Anjuli Patricia Kannan

Rick A Hamilton, Ii

Ossama S Emam

Brian E D Kingsbury

Maria Carolina Parada San Martin

Antoine Jean Bruguier

Dan Jiang

Shuo-Yiin Chang

Rami Botros

Andrew William Senior

Khe Chai Sim

Jiahui Yu

Pedro Jose Moreno Mengibar

Lior Horesh

Michael Alan Picheny

Anirban Basu

Eugene Weinstein

Samuel Bengio

Vikas Sindhwani

Izhak Shafran

Weiran Wang

Rick Hamilton

Christopher Walter George Thornton

Yangzhang He

Charles Caleb Peyser

Ronny Huang

Zelin Wu

Hariklia Deligianni

Pamela Ann Nesbitt

Oriol Vinyals

Yu Zhang

Hasim Sak

Rajeev Conrad Nongpiur

Navdeep Jaitly

George Andrei Saon

Sachin Gupta

Elizabeth Vera Woodward

Marc Yvon

Kanury Kanishka Rao

Gabor Simko

Wilfredo Ferre

Chanwoo Kim

Ankur Bapna

Basilio Garcia Castillo

Qiao Liang

Guoguo Chen

Anmol Gulati

Cyril Allauzen

Shuo-yiin Chang

Brian Kingsbury

Nina Sainath

Jan Kazimierz Chorowski

Deepti Bhatia

Ekaterina Gonina

Wei Ping Li

Carlos Henrique Cardonha

Vaibhava Goel

Etienne Marcheret

Wei Li

Neeraj Gaur

Wei Han

Parisa Haghani

Petr Fousek

Vijayaditya Peddinti

Guru Prakash Arumugam

Krzysztof Marcin Choromanski

Tongzhou Chen

Manaal Faruqui

Andrew W Senior

Qiumin Xu

Yedid Hoshen

A computer-implemented method includes receiving audio data that corresponds to an utterance spoken by a user and captured by a user device. The method also includes processing the audio data to determine a candidate transcription that includes a sequence of tokens for the spoken utterance. Tor each token in the sequence of tokens, the method includes determining a token embedding for corresponding token, determining a n-gram token embedding for a previous sequence of n-gram tokens, and concatenating the token embedding and the n-gram token embedding to generate a concatenated output for the corresponding token. The method also includes rescoring the candidate transcription for the spoken utterance by processing the concatenated output generated for each corresponding token in the sequence of tokens.

Lookup-table recurrent language model

A method includes receiving a training example that includes audio data representing a spoken utterance and a ground truth transcription. For each word in the spoken utterance, the method also includes inserting a placeholder symbol before the respective word identifying a respective ground truth alignment for a beginning and an end of the respective word, determining a beginning word piece and an ending word piece, and generating a first constrained alignment for the beginning word piece and a second constrained alignment for the ending word piece. The first constrained alignment is aligned with the ground truth alignment for the beginning of the respective word and the second constrained alignment is aligned with the ground truth alignment for the ending of the respective word. The method also includes constraining an attention head of a second pass decoder by applying the first and second constrained alignments.

Emitting word timings with end-to-end models

A method of text-only and semi-supervised training for deliberation includes receiving training data including unspoken textual utterances that are each not paired with any corresponding spoken utterance of non-synthetic speech, and training a deliberation model that includes a text encoder and a deliberation decoder on the unspoken textual utterances. The method also includes receiving, at the trained deliberation model, first-pass hypotheses and non-causal acoustic embeddings. The first-pass hypotheses is generated by a recurrent neural network-transducer (RNN-T) decoder for the non-causal acoustic embeddings encoded by a non-causal encoder. The method also includes encoding, using the text encoder, the first-pass hypotheses generated by the RNN-T decoder, and generating, using the deliberation decoder attending to both the first-pass hypotheses and the non-causal acoustic embeddings, second-pass hypotheses.

Deliberation by text-only and semi-supervised training

A method includes generating, using an audio encoder, a higher-order feature representation for each acoustic frame in a sequence of acoustic frames; generating, using a decoder, based on the higher-order feature representation, a plurality of speech recognition hypotheses, each hypotheses corresponding to a candidate transcription of an utterance and having an associated first likelihood score; generating, using an external language model, for each speech recognition hypothesis, a second likelihood score; determining, using a learnable fusion module, for each speech recognition hypothesis, a set of fusion weights based on the higher-order feature representation and the speech recognition hypothesis; and generating, using the learnable fusion module, for each speech recognition hypothesis, a third likelihood score based on the first likelihood score, the second likelihood score, and the set of fusion weights, the audio encoder and decoder trained using minimum additive error rate training in the presence of the external language model.

Rare word recognition with LM-aware MWER training

A method includes receiving a sequence of input audio frames corresponding to an utterance captured by a user device, the utterance including a plurality of words. For each input audio frame, the method includes predicting, using a word boundary detection model configured receive the sequence of input audio frames as input, whether the input audio frame is a word boundary. The method includes batching the input audio frames into a plurality of batches based on the input audio frames predicted as word boundaries, wherein each batch includes a corresponding plurality of batched input audio frames. For each of the plurality of batches, the method includes processing, using a speech recognition model, the corresponding plurality of batched input audio frames in parallel to generate a speech recognition result.

Predicting word boundaries for on-device batching of end-to-end speech recognition models

A method includes receiving, as input to a speech recognition model, audio data corresponding to a spoken utterance. The method also includes performing, using the speech recognition model, speech recognition on the audio data by, at each of a plurality of time steps, encoding, using an audio encoder, the audio data corresponding to the spoken utterance into a corresponding audio encoding, and decoding, using a speech recognition joint network, the corresponding audio encoding into a probability distribution over possible output labels. At each of the plurality of time steps, the method also includes determining, using an intended query (IQ) joint network configured to receive a label history representation associated with a sequence of non-blank symbols output by a final softmax layer, an intended query decision indicating whether or not the spoken utterance includes a query intended for a digital assistant.

Intended query detection using E2E modeling for continued conversation

Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.

Multi-dialect and multilingual speech recognition

A method includes receiving audio features and generating a latent speech representation based on the audio features. The method also includes generating a target quantized vector token and a target token index for a corresponding latent speech representation. The method also includes generating a contrastive context vector for a corresponding unmasked or masked latent speech representation and deriving a contrastive self-supervised loss based on the corresponding contrastive context vector and the corresponding target quantized vector token. The method also include generating a high-level context vector based on the contrastive context vector and, for each high-level context vector, learning to predict the target token index at the corresponding time step using a cross-entropy loss based on the target token index. The method also includes predicting speech recognition hypotheses for the utterance and training a multilingual automatic speech recognition (ASR) model using an unsupervised loss and a supervised loss.

Joint unsupervised and supervised training for multilingual ASR

A speech recognition model includes an encoder network, a prediction network, and a joint network. The encoder network is configured to receive a sequence of acoustic frames characterizing an input utterance; and generate, at each of a plurality of output steps, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The prediction network is configured to: receive a sequence of non-blank symbols output by a final Softmax layer; and generate, at each of the plurality of output steps, a dense representation. The joint network is configured to generate, at each of the plurality of output steps based on the higher order feature representation and the dense representation, a probability distribution over possible speech recognition hypotheses. The joint network includes a stack of gating and bilinear pooling to fuse the dense representation and the higher order feature representation.

Fusion of acoustic and text representations in RNN-T

A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Optimizing inference performance for conformer

A method includes receiving a sequence of acoustic frames characterizing one or more utterances as input to a multilingual automated speech recognition (ASR) model. The method also includes generating a higher order feature representation for a corresponding acoustic frame. The method also includes generating a hidden representation based on a sequence of non-blank symbols output by a final softmax layer. The method also includes generating a probability distribution over possible speech recognition hypotheses based on the hidden representation generated by the prediction network at each of the plurality of output steps and the higher order feature representation generated by the encoder at each of the plurality of output steps. The method also includes predicting an end of utterance (EOU) token at an end of each utterance. The method also includes classifying each acoustic frame as either speech, initial silence, intermediate silence, or final silence.

Language agnostic multilingual end-to-end streaming on-device ASR system

An automated speech recognition (ASR) model includes a first encoder, a second encoder, and a decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The second encoder receives, as input, the first higher order feature representation generated by the first encoder at each of the plurality of output steps, and generates, at each of the plurality of output steps, a second higher order feature representation for a corresponding first higher order feature frame. The decoder receives, as input, the second higher order feature representation generated by the second encoder at each of the plurality of output steps, and generates, at each of the plurality of time steps, a first probability distribution over possible speech recognition hypotheses.

Cascaded encoders for simplified streaming and non-streaming ASR

A method includes receiving a sequence of acoustic frames and generating, by a first encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by a first pass transducer decoder, a first pass speech recognition hypothesis for a corresponding first higher order feature representation and generating, by a text encoder, a text encoding for a corresponding first pass speech recognition hypothesis. The method also includes generating, by a second encoder, a second higher order feature representation for a corresponding first higher order feature representation. The method also includes generating, by a second pass transducer decoder, a second pass speech recognition hypothesis using a corresponding second higher order feature representation and a corresponding text encoding.

Transducer-based streaming deliberation for cascaded encoders

A method for performing speech recognition using sequence-to-sequence models includes receiving audio data for an utterance and providing features indicative of acoustic characteristics of the utterance as input to an encoder. The method also includes processing an output of the encoder using an attender to generate a context vector, generating speech recognition scores using the context vector and a decoder trained using a training process, and generating a transcription for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.

Speech recognition with sequence-to-sequence models

A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.

Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment lattice

Growing community of inventors

New York, NY, United States of America

Tara N Sainath