Google Inc.

Microsoft Technology Licensing, LLC

Waymo LLC

Patrick An Phu Nguyen

Zhifeng Chen

Yonghui Wu

Tara N Sainath

Ron J Weiss

Bo Li

Rohit Prakash Prabhavalkar

Chung-Cheng Chiu

Anjuli Patricia Kannan

Pedro Jose Moreno Mengibar

Vincent Olivier Vanhoucke

David Kryze

Eugene Weinstein

Khe Chai Sim

Theodore Vassilakis

Ignacio Lopez Moreno

Yu Zhang

Ruoming Pang

Apostolos Lerios

Quan Wang

Navdeep Jaitly

Michiel A U Bacchiani

Kanury Kanishka Rao

Ye Jia

Georg Heigold

Jonathan Shen

Sreenivasa R Viswanadha

Fei Ren

Jan Kazimierz Chorowski

Ekaterina Gonina

Jeffrey Adgate Dean

Andrew William Senior

Oriol Vinyals

Johan Schalkwyk

Jonathon Shlens

Vijay Vasudevan

Maria Carolina Parada San Martin

Matthieu Devin

Xin Lei

Jiquan Ngiam

Ouais Alsharif

Yin Zhou

Eric Karlson

Pei Sun

Yuning Chai

Mitchel Weintraub

Wei Han

Benjamin James Caine

Brandon Chauloon Yang

Marc'aurelio Ranzato

Laurent An Minh Nguyen

Xi Yi

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 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

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-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

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 N-best lists of decoded hypotheses, 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.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Object detection in point clouds

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.

Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to receive at least one database query to be executed. At least one computation graph corresponding to the at least one database query is generated. The computation graph is transformed to an optimized computation graph. The respective portions of the optimized computation graph are distributed to a plurality of distributed computing systems for execution. A result for the at least one database query is provided.

Optimization of database queries via transformations of computation graph

Audio data that encodes an utterance of a user is received. It is determined that the user has been classified as a novice user of a speech recognizer. A speech recognizer setting is selected that is used by the speech recognizer in generating a transcription of the utterance. The selected speech recognizer setting is different than a default speech recognizer setting that is used by the speech recognizer in generating transcriptions of utterances of users that are not classified as novice users. The selected speech recognizer setting results in increased speech recognition accuracy in comparison with the default setting. A transcription of the utterance is obtained that is generated by the speech recognizer using the selected setting.

Speech recognition parameter adjustment

Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to receive at least one database query to be executed. Code corresponding to the at least one database query can be generated. One or more optimizations to the generated code can be performed to produce specialized modular code. The one or more optimizations can include Just-In-Time (JIT) compilation techniques. Respective portions of the code can be distributed to a plurality of distributed computing systems for execution, wherein each of the distributed computing systems is connected to a portion of the plurality of distributed computing systems. A result for the at least one database query can be provided.

Systems and methods for a distributed query execution engine

Various embodiments can include systems, methods, and non-transitory computer readable media configured to receive at least one operation to be performed using (i) first data that is managed by a first computing system and (ii) second data that is managed by a second computing system, the operation being received through an interface provided by the computing system, and wherein the operation is based at least in part on a Structured Query Language (SQL). At least one optimization can be performed based at least in part on the operation. The operation can be executed using at least the first data and the second data. A result generated can be provided upon executing the operation through the interface provided by the computing system. The computing system, the first computing system, and the second computing system are each able to concurrently process, access, and create at least a portion of the generated result.

Systems and methods for an SQL-driven distributed operating system

Growing community of inventors

Palo Alto, CA, United States of America

Patrick An Phu Nguyen