Google Inc.

Merck Sharp + Dohme Corp.

Waymo LLC

Zhifeng Chen

Yonghui Wu

Ron J Weiss

Patrick An Phu Nguyen

Tara N Sainath

Navdeep Jaitly

Lan Zhang

Michael Schuster

Aimin Tang

Kalpit A Vora

Kara S Cox

Daniel DiStefano

Hua-Poo Su

Quoc V Le

Yu Zhang

Ioannis Agiomyrgiannakis

Ryan Michael Rifkin

Ye Jia

Yuxuan Wang

Zongheng Yang

Bo Li

Ruoming Pang

Rohit Prakash Prabhavalkar

Chung-Cheng Chiu

Melvin Jose Johnson Premkumar

Jonathan Shen

Anjuli Patricia Kannan

Jonathon Shlens

Samuel Bengio

Jiquan Ngiam

Wolfgang Macherey

Robert Andrew James Clark

Russell John Wyatt Skerry-Ryan

Russell J Ryan

Ying Xiao

Pedro Jose Moreno Mengibar

Ignacio Lopez Moreno

Quan Wang

Vijay Vasudevan

Eugene Weinstein

Niki J Parmar

Khe Chai Sim

Ouais Alsharif

Llion Owen Jones

Ankur Bapna

Wei Han

Orhan Firat

Macduff Richard Hughes

Benjamin James Caine

Xu Chen

George Foster

Brandon Chauloon Yang

Fei Ren

Bhuvana Ramabhadran

Thorsten Brants

Chen Wu

Michiel A U Bacchiani

Andrew M Rosenberg

Byungha Chun

Kanury Kanishka Rao

Junhua Mao

Zhengdong Zhang

Christoph Sprunk

Maxim Krikun

Jan Kazimierz Chorowski

Ekaterina Gonina

Fadi Biadsy

Mohammad Norouzi

Yin Zhou

Pei Sun

Yuning Chai

Yanping Huang

Patrick An Nguyen

Dehao Chen

Nichola Abdo

Christopher John Sweeney

Youlong Cheng

HyoukJoong Lee

Xi Yi

Melvin Johnson

Philipp Florian Jund

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.

Machine translation using neural network models

The present invention relates to monoclonal antibodies which have high anti-RSV neutralizing titers. The invention further provides for isolated nucleic acids encoding the antibodies of the invention and host cells transformed therewith. The invention yet further provides for diagnostic, prophylactic and therapeutic methods employing the antibodies and nucleic acids of the invention, particularly as a passive immunotherapy agent in infants and the elderly.

Antibody neutralizing human respiratory syncytial virus

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

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 apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. The methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.

Synthesis of speech from text in a voice of a target speaker using neural networks

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

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting scene flow. One of the methods includes obtaining a current point cloud representing an observed scene at a current time point; obtaining object label data that identifies a first three-dimensional region in the observed scene; determining, for each current three-dimensional point that is within the first three-dimensional region and using the object label data, a respective preceding position of the current three-dimensional point at a preceding time point in a reference frame of the sensor at the current time point; and generating, using the preceding positions, a scene flow label for the current point cloud that comprises a respective ground truth motion vector for each of a plurality of the current three-dimensional points.

Generating scene flow labels for point clouds using object labels

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 an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.

Multilingual speech synthesis and cross-language voice cloning

The present disclosure provides systems and methods that train and use machine-learned models such as, for example, sequence-to-sequence models, to perform direct and text-free speech-to-speech translation. In particular, aspects of the present disclosure provide an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation.

Direct speech-to-speech translation via machine learning

Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Minimum word error rate training for attention-based sequence-to-sequence models

Growing community of inventors

Sunnyvale, CA, United States of America

Zhifeng Chen