公开(公告)号：US20230343328A1

公开(公告)日：2023-10-26

申请号：US18336211

申请日：2023-06-16

Applicant: Google LLC

Inventor： Tara Sainath ,  Arun Narayanan ,  Rami Botros ,  Yanzhang He ,  Ehsan Variani ,  Cyril Allauzen ,  David Rybach ,  Ruoming Pang ,  Trevor Strohman

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/22 ,  G10L15/30

CPC classification number: G10L15/063 ,  G10L15/02 ,  G10L15/22 ,  G10L15/30

Abstract: An ASR model includes a first encoder configured to receive a sequence of acoustic frames and generate a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The ASR model also includes a second encoder configured to receive the first higher order feature representation generated by the first encoder at each of the plurality of output steps and generate a second higher order feature representation for a corresponding first higher order feature frame. The ASR model also includes a decoder configured to receive the second higher order feature representation generated by the second encoder at each of the plurality of output steps and generate a first probability distribution over possible speech recognition hypothesis. The ASR model also includes a language model configured to receive the first probability distribution over possible speech hypothesis and generate a rescored probability distribution.

公开(公告)号：US11556381B2

公开(公告)日：2023-01-17

申请号：US17738909

申请日：2022-05-06

Applicant: Google LLC

Inventor： Jeffrey Adgate Dean ,  Sudip Roy ,  Michael Acheson Isard ,  Aakanksha Chowdhery ,  Brennan Saeta ,  Chandramohan Amyangot Thekkath ,  Daniel William Hurt ,  Hyeontaek Lim ,  Laurent El Shafey ,  Parker Edward Schuh ,  Paul Ronald Barham ,  Ruoming Pang ,  Ryan Sepassi ,  Sanjay Ghemawat ,  Yonghui Wu

IPC: G06F15/82 ,  G06F9/48 ,  G06N3/08 ,  G06N3/063

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators. One of the systems comprises a plurality of accelerator islands, each hardware accelerator island comprising a respective plurality of hardware devices that include a plurality of hardware accelerators and a corresponding host for each of the plurality of hardware accelerators; and a respective scheduler for each of the accelerator islands that is configured to schedule workloads across the plurality of accelerators and corresponding hosts in the accelerator island, wherein the system is configured to: receive data representing a machine learning workload; and assign a respective portion of the machine learning workload to each of the plurality of accelerator islands for scheduling by the respective scheduler for the accelerator island.

公开(公告)号：US20220189456A1

公开(公告)日：2022-06-16

申请号：US17455667

申请日：2021-11-18

Applicant: Google LLC

Inventor： Ruoming Pang ,  Andros Tjandra ,  Yu Zhang ,  Shigeki Karita

IPC: G10L13/027 ,  G10L21/0308

Abstract: A linguistic content and speaking style disentanglement model includes a content encoder, a style encoder, and a decoder. The content encoder is configured to receive input speech as input and generate a latent representation of linguistic content for the input speech output. The content encoder is trained to disentangle speaking style information from the latent representation of linguistic content. The style encoder is configured to receive the input speech as input and generate a latent representation of speaking style for the input speech as output. The style encoder is trained to disentangle linguistic content information from the latent representation of speaking style. The decoder is configured to generate output speech based on the latent representation of linguistic content for the input speech and the latent representation of speaking style for the same or different input speech.

公开(公告)号：US20220122622A1

公开(公告)日：2022-04-21

申请号：US17237021

申请日：2021-04-21

Applicant: Google LLC

Inventor： Arun Narayanan ,  Tara Sainath ,  Chung-Cheng Chiu ,  Ruoming Pang ,  Rohit Prabhavalkar ,  Jiahui Yu ,  Ehsan Variani ,  Trevor Strohman

IPC: G10L19/16 ,  G10L15/00 ,  G10L25/30 ,  G06N3/08

Abstract: 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.

公开(公告)号：US12293276B2

公开(公告)日：2025-05-06

申请号：US18430483

申请日：2024-02-01

Applicant: Google LLC

Inventor： Mingxing Tan ,  Quoc Le ,  Bo Chen ,  Vijay Vasudevan ,  Ruoming Pang

IPC: G06N3/04 ,  G06F17/15 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/10

Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

公开(公告)号：US20250077833A1

公开(公告)日：2025-03-06

申请号：US18821971

申请日：2024-08-30

Applicant: Google LLC

Inventor： Sheng Li ,  Norman Paul Jouppi ,  Quoc V. Le ,  Mingxing Tan ,  Ruoming Pang ,  Liqun Cheng ,  Andrew Li

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining an architecture for a task neural network that is configured to perform a particular machine learning task on a target set of hardware resources. When deployed on a target set of hardware, such as a collection of datacenter accelerators, the task neural network may be capable of performing the particular machine learning task with enhanced accuracy and speed.

公开(公告)号：US20250053444A1

公开(公告)日：2025-02-13

申请号：US18814371

申请日：2024-08-23

Applicant: Google LLC

Inventor： Jeffrey Adgate Dean ,  Sudip Roy ,  Michael Acheson Isard ,  Aakanksha Chowdhery ,  Brennan Saeta ,  Chandramohan Amyangot Thekkath ,  Daniel William Hurt ,  Hyeontaek Lim ,  Laurent El Shafey ,  Parker Edward Schuh ,  Paul Ronald Barham ,  Ruoming Pang ,  Ryan Sepassi ,  Sanjay Ghemawat ,  Yonghui Wu

IPC: G06F9/48 ,  G06N3/063 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators. One of the systems comprises a plurality of accelerator islands, each hardware accelerator island comprising a respective plurality of hardware devices that include a plurality of hardware accelerators and a corresponding host for each of the plurality of hardware accelerators; and a respective scheduler for each of the accelerator islands that is configured to schedule workloads across the plurality of accelerators and corresponding hosts in the accelerator island, wherein the system is configured to: receive data representing a machine learning workload; and assign a respective portion of the machine learning workload to each of the plurality of accelerator islands for scheduling by the respective scheduler for the accelerator island.

公开(公告)号：US20250037426A1

公开(公告)日：2025-01-30

申请号：US18716912

申请日：2022-12-09

Applicant: Google LLC

Inventor： Bowen Zhang ,  Jiahui Yu ,  Christopher Fifty ,  Wei Han ,  Andrew M. Dai ,  Ruoming Pang ,  Fei Sha

IPC: G06V10/764 ,  G06V10/774

Abstract: A method includes obtaining video datasets each including pairs of a training video and a ground-truth action classification of the training video. The method also includes generating an action recognition model that includes a shared encoder model and action classification heads. A number of the action classifications heads may be equal to a number of the video datasets, and each action classification head may be configured to, based on an output of the shared encoder model, classify training videos sampled from a corresponding video dataset. The method also includes determining, by the action recognition model and for each training video sampled from the video datasets, an inferred action classification. The method further includes determining a loss value based on the inferred action classifications and the ground-truth action classifications, and adjusting parameters of the action recognition model based on the loss value.

公开(公告)号：US12131244B2

公开(公告)日：2024-10-29

申请号：US17039178

申请日：2020-09-30

Applicant: Google LLC

Inventor： Sheng Li ,  Norman Paul Jouppi ,  Quoc V. Le ,  Mingxing Tan ,  Ruoming Pang ,  Liqun Cheng ,  Andrew Li

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining an architecture for a task neural network that is configured to perform a particular machine learning task on a target set of hardware resources. When deployed on a target set of hardware, such as a collection of datacenter accelerators, the task neural network may be capable of performing the particular machine learning task with enhanced accuracy and speed.

公开(公告)号：US12118988B2

公开(公告)日：2024-10-15

申请号：US17933307

申请日：2022-09-19

Applicant: Google LLC

Inventor： Ke Hu ,  Tara N. Sainath ,  Arun Narayanan ,  Ruoming Pang ,  Trevor Strohman

IPC: G10L15/197 ,  G06F40/126 ,  G10L15/02 ,  G10L15/06 ,  G10L15/08 ,  G10L15/22

CPC classification number: G10L15/197 ,  G06F40/126 ,  G10L15/02 ,  G10L15/063 ,  G10L15/083 ,  G10L15/22

Abstract: 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.