公开(公告)号：US20240161729A1

公开(公告)日：2024-05-16

申请号：US18418025

申请日：2024-01-19

Applicant: DeepMind Technologies Limited

Inventor： Luis Carlos Cobo Rus ,  Nal Kalchbrenner ,  Erich Elsen ,  Chenjie Gu

IPC: G10L13/047 ,  G10L13/08 ,  G10L25/30

CPC classification number: G10L13/047 ,  G10L13/08 ,  G10L25/30

Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.

公开(公告)号：US11915682B2

公开(公告)日：2024-02-27

申请号：US17610934

申请日：2019-05-20

Applicant: DeepMind Technologies Limited

Inventor： Luis Carlos Cobo Rus ,  Nal Kalchbrenner ,  Erich Elsen ,  Chenjie Gu

IPC: G10L13/00 ,  G10L19/00 ,  G10L13/047 ,  G10L13/08 ,  G10L25/30

CPC classification number: G10L13/047 ,  G10L13/08 ,  G10L25/30

Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.

公开(公告)号：US12211484B2

公开(公告)日：2025-01-28

申请号：US18418025

申请日：2024-01-19

Applicant: DeepMind Technologies Limited

Inventor： Luis Carlos Cobo Rus ,  Nal Kalchbrenner ,  Erich Elsen ,  Chenjie Gu

IPC: G10L25/30 ,  G10L13/00 ,  G10L13/047 ,  G10L13/08

Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.

公开(公告)号：US20220254330A1

公开(公告)日：2022-08-11

申请号：US17610934

申请日：2019-05-20

Applicant: DeepMind Technologies Limited

Inventor： Luis Carlos Cobo Rus ,  Nal Kalchbrenner ,  Erich Elsen ,  Chenjie Gu

IPC: G10L13/047 ,  G10L13/08 ,  G10L25/30

Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.