Google Inc.

Navdeep Jaitly

Quoc V Le

Oriol Vinyals

Noam M Shazeer

Yonghui Wu

Ron J Weiss

Zhifeng Chen

William Chan

Samuel Bengio

Ioannis Agiomyrgiannakis

Ryan Michael Rifkin

Yuxuan Wang

Zongheng Yang

Ilya Sutskever

Chung-Cheng Chiu

Robert Andrew James Clark

Russell J Ryan

Ying Xiao

Samy Bengio

Yu Zhang

Christopher S Co

Katherine Irene Chou

Ananth Sankar

Lily Hao Yi Peng

Tara N Sainath

Bo Li

Ruoming Pang

Rohit Prakash Prabhavalkar

Michiel A U Bacchiani

Geoffrey Everest Hinton

Patrick An Phu Nguyen

Yu Shrike Zhang

Kanury Kanishka Rao

Jonathan Shen

Michael Schuster

Russell John Wyatt Skerry-Ryan

Anjuli Patricia Kannan

Yuping Luo

Jan Kazimierz Chorowski

Ekaterina Gonina

Chitwan Saharia

Mohammad Norouzi

John Dieterich Lawson

George Jay Tucker

Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

Generating structured text content using speech recognition models

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sequence modeling. One of the methods includes receiving an input sequence having a plurality of input positions; determining a plurality of blocks of consecutive input positions; processing the input sequence using a neural network to generate a latent alignment, comprising, at each of a plurality of input time steps: receiving a partial latent alignment from a previous input time step; selecting an input position in each block, wherein the token at the selected input position of the partial latent alignment in each block is a mask token; and processing the partial latent alignment and the input sequence using the neural network to generate a new latent alignment, wherein the new latent alignment comprises, at the selected input position in each block, an output token or a blank token; and generating, using the latent alignment, an output sequence.

Sequence modeling using imputation

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

End-to-end text-to-speech conversion

Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.

Synthesizing speech from text using neural networks

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

Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Speech recognition with attention-based recurrent neural networks

This document generally describes a neural network training system, including one or more computers, that trains a recurrent neural network (RNN) to receive an input, e.g., an input sequence, and to generate a sequence of outputs from the input sequence. In some implementations, training can include, for each position after an initial position in a training target sequence, selecting a preceding output of the RNN to provide as input to the RNN at the position, including determining whether to select as the preceding output (i) a true output in a preceding position in the output order or (ii) a value derived from an output of the RNN for the preceding position in an output order generated in accordance with current values of the parameters of the recurrent neural network.

Training recurrent neural networks to generate sequences

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence from a source sequence. In one aspect, the system includes a recurrent neural network configured to, at each time step, receive an input for the time step and process the input to generate a progress score and a set of output scores; and a subsystem configured to, at each time step, generate the recurrent neural network input and provide the input to the recurrent neural network; determine, from the progress score, whether or not to emit a new output at the time step; and, in response to determining to emit a new output, select an output using the output scores and emit the selected output as the output at a next position in the output order.

Recurrent neural networks for online sequence generation

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences from input sequences. One of the methods includes obtaining an input sequence having a first number of inputs arranged according to an input order; processing each input in the input sequence using an encoder recurrent neural network to generate a respective encoder hidden state for each input in the input sequence; and generating an output sequence having a second number of outputs arranged according to an output order, each output in the output sequence being selected from the inputs in the input sequence, comprising, for each position in the output order: generating a softmax output for the position using the encoder hidden states that is a pointer into the input sequence; and selecting an input from the input sequence as the output at the position using the softmax output.

Generating output sequences from input sequences using neural networks

A system can be configured to perform tasks such as converting recorded speech to a sequence of phonemes that represent the speech, converting an input sequence of graphemes into a target sequence of phonemes, translating an input sequence of words in one language into a corresponding sequence of words in another language, or predicting a target sequence of words that follow an input sequence of words in a language (e.g., a language model). In a speech recognizer, the RNN system may be used to convert speech to a target sequence of phonemes in real-time so that a transcription of the speech can be generated and presented to a user, even before the user has completed uttering the entire speech input.

Generating target sequences from input sequences using partial conditioning

A computer-implemented method for training a neural network that is configured to generate a score distribution over a set of multiple output positions. The neural network is configured to process a network input to generate a respective score distribution for each of a plurality of output positions including a respective score for each token in a predetermined set of tokens that includes n-grams of multiple different sizes. Example methods described herein provide trained neural networks which produce results with improved accuracy compared to the state of the art, e.g. translations that are more accurate compared to the state of the art, or more accurate speech recognition compared to the state of the art.

Processing text sequences using neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps, processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence, processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.

Growing community of inventors

Mountain View, CA, United States of America

Navdeep Jaitly