Google Inc.

Other

Rohit Prakash Prabhavalkar

Tara N Sainath

Trevor D Strohman

Chung-Cheng Chiu

Yonghui Wu

Michiel A U Bacchiani

Arun Narayanan

Golan Pundak

Antoine Jean Bruguier

Neeraj Gaur

Ke Hu

Pedro Jose Moreno Mengibar

Yaniv Leviathan

Zhifeng Chen

Yanzhang He

Patrick An Phu Nguyen

Tomer Amiaz

Asaf Aharoni

Ian C McGraw

Parisa Haghani

Anjuli Patricia Kannan

Bo Li

Ruoming Pang

Kanury Kanishka Rao

Wei Ping Li

Ron J Weiss

Navdeep Jaitly

Ehsan Variani

Wei Li

Ouais Alsharif

Qiao Liang

Bhuvana Ramabhadran

Jakob Nicolaus Foerster

Yu Zhang

Giovanni Motta

Diamantino Antonio Caseiro

Françoise Beaufays

Gabor Simko

Rajiv Mathews

David Rybach

Li Wei

Austin Severn Waters

Zhongdi Qu

Galen Tsai Chuang

Nir Shabat

Weiran Wang

Yangzhang He

Ian Mcgraw

Liangliang Cao

Sepand Mavandadi

Anton Bakhtin

Ekaterina Gonina

Jan Kazimierz Chorowski

Jiahui Yu

Rami Botros

Tongzhou Chen

Mirkó Visontai

Zhiyun Lu

Cyril Allauzen

Christopher Walter George Thornton

Shuo-yiin Chang

Shaojin Ding

David Qiu

Charles Caleb Peyser

Chao Zhang

Ronny Huang

Lillian Zhou

Qiujia Li

Deepti Bhatia

Ding Zhao

Thibault Doutre

Dhruv Guliani

Rina Panigrahy

Robert David

Dongseong Hwang

Xin Wang

Patrick Maxim Rondon

Harry Zhang

Mingqing Chen

Yanwei Pan

Michiel Au Bacchiani

Tara C Sainath

Ian C Mcgraw

A method includes receiving context biasing data that includes a set of unspoken textual utterances corresponding to a particular context. The method also includes obtaining a list of carrier phrases associated with the particular context. For each respective unspoken textual utterance, the method includes generating a corresponding training data pair that includes the respective unspoken textual utterance and a carrier phrase. For each respective training data pair, the method includes tokenizing the respective training data pair into a sequence of sub-word units, generating a first higher order textual feature representation for a corresponding sub-word unit, receiving the first higher order textual feature representation, and generating a first probability distribution over possible text units. The method also includes training a speech recognition model based on the first probability distribution over possible text units.

Contextual biasing with text injection

A method includes obtaining a set of training samples, wherein each training sample includes a corresponding sequence of speech segments corresponding to a training utterance and a corresponding sequence of ground-truth transcriptions for the sequence of speech segments, and wherein each ground-truth transcription includes a start time and an end time of a corresponding speech segment. For each training sample in the set of training samples, the method includes processing, using a speech recognition model, the corresponding sequence of speech segments to obtain one or more speech recognition hypotheses for the training utterance; and, for each speech recognition hypothesis obtained for the training utterance, identifying a respective number of word errors relative to the corresponding sequence of ground-truth transcriptions. The method trains the speech recognition model to minimize word error rate based on the respective number of word errors identified for each speech recognition hypothesis obtained for the training utterance.

Training for long-form speech recognition

Two-pass automatic speech recognition (ASR) models can be used to perform streaming on-device ASR to generate a text representation of an utterance captured in audio data. Various implementations include a first-pass portion of the ASR model used to generate streaming candidate recognition(s) of an utterance captured in audio data. For example, the first-pass portion can include a recurrent neural network transformer (RNN-T) decoder. Various implementations include a second-pass portion of the ASR model used to revise the streaming candidate recognition(s) of the utterance and generate a text representation of the utterance. For example, the second-pass portion can include a listen attend spell (LAS) decoder. Various implementations include a shared encoder shared between the RNN-T decoder and the LAS decoder.

Two-pass end to end speech recognition

An automated speech recognition (ASR) model includes a first encoder, a first encoder, a second encoder, and a second 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 first decoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a first probability distribution over possible speech recognition hypotheses. The second encoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a second higher order feature representation for a corresponding first higher order feature frame. The second decoder receives, as input, the second higher order feature representation generated by the second encoder, and generates a second probability distribution over possible speech recognition hypotheses.

Unified cascaded encoder ASR model for dynamic model sizes

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

Implementations described herein identify and correct automatic speech recognition (ASR) misrecognitions. For example, on-device processor(s) of a client device may generate a predicted textual segment that is predicted to correspond to spoken utterance of a user of the client device, and may receive further input that modifies the predicted textual segment to an alternate textual segment. Further, the on-device processor(s) may store these textual segments in on-device storage as a candidate correction pair, and transmit the candidate correction pair to a remote system. Moreover, remote processor(s) of the remote system may determine that the candidate correction pair is an actual correction pair, and may cause client devices to generate updates for a global ASR model for the candidate correction pair. Additionally, the remote processor(s) may distribute the global ASR model to the client devices and/or additional client devices.

Identifying and correcting automatic speech recognition (ASR) misrecognitions in a decentralized manner

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

Automated calling 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 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 method includes receiving audio data encoding an utterance and obtaining a set of bias phrases corresponding to a context of the utterance. Each bias phrase includes one or more words. The method also includes processing, using a speech recognition model, acoustic features derived from the audio to generate an output from the speech recognition model. The speech recognition model includes a first encoder configured to receive the acoustic features, a bias encoder configured to receive data indicating the obtained set of bias phrases, a bias encoder, and a decoder configured to determine likelihoods of sequences of speech elements based on output of the first attention module and output of the bias attention module. The method also includes determining a transcript for the utterance based on the likelihoods of sequences of speech elements.

Contextual biasing for speech recognition

A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis.

Deliberation model-based two-pass end-to-end speech recognition

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a compressed recurrent neural network (RNN). One of the systems includes a compressed RNN, the compressed RNN comprising a plurality of recurrent layers, wherein each of the recurrent layers has a respective recurrent weight matrix and a respective inter-layer weight matrix, and wherein at least one of recurrent layers is compressed such that a respective recurrent weight matrix of the compressed layer is defined by a first compressed weight matrix and a projection matrix and a respective inter-layer weight matrix of the compressed layer is defined by a second compressed weight matrix and the projection matrix.

Compressed recurrent neural network models

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting utterances of a key phrase in an audio signal. One of the methods includes receiving, by a key phrase spotting system, an audio signal encoding one or more utterances; while continuing to receive the audio signal, generating, by the key phrase spotting system, an attention output using an attention mechanism that is configured to compute the attention output based on a series of encodings generated by an encoder comprising one or more neural network layers; generating, by the key phrase spotting system and using attention output, output that indicates whether the audio signal likely encodes the key phrase; and providing, by the key phrase spotting system, the output that indicates whether the audio signal likely encodes the key phrase.

Key phrase spotting

Growing community of inventors

Santa Clara, CA, United States of America

Rohit Prakash Prabhavalkar