公开(公告)号：US11756529B2

公开(公告)日：2023-09-12

申请号：US17123253

申请日：2020-12-16

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Liao Zhang ,  Xiaoyin Fu ,  Zhengxiang Jiang ,  Mingxin Liang ,  Junyao Shao ,  Qi Zhang ,  Zhijie Chen ,  Qiguang Zang

IPC: G10L15/02 ,  G06F40/12 ,  G06F40/30 ,  G06F7/78 ,  G06F17/16 ,  G10L15/26

CPC classification number: G10L15/02 ,  G06F7/78 ,  G06F17/16 ,  G06F40/12 ,  G06F40/30 ,  G10L15/26 ,  G10L2015/025

Abstract: Proposed are a method and apparatus for speech recognition, and a storage medium. The specific solution includes: obtaining audio data to be recognized; decoding the audio data to obtain a first syllable of a to-be-converted word, in which the first syllable is a combination of at least one phoneme corresponding to the to-be-converted word; obtaining a sentence to which the to-be-converted word belongs and a converted word in the sentence, and obtaining a second syllable of the converted word; encoding the first syllable and the second syllable to generate first encoding information of the first syllable; and decoding the first encoding information to obtain a text corresponding to the to-be-converted word.

公开(公告)号：US11893988B2

公开(公告)日：2024-02-06

申请号：US17357598

申请日：2021-06-24

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Song Yang ,  Saisai Zou ,  Jieyi Cao ,  Junyao Shao

IPC: G10L15/22 ,  G06F16/635 ,  G10L15/05

CPC classification number: G10L15/22 ,  G06F16/635 ,  G10L15/05 ,  G10L2015/223

Abstract: The disclosure provides a speech control method, a speech control apparatus, an electronic device, and a storage medium. The method includes: acquiring target audio data sent by a client, the target audio data including audio data collected by the client within a target duration before wake-up and audio data collected by the client after wake-up; performing speech recognition on the target audio data; and controlling the client based on an instruction recognized from a second audio segment of the target audio data in response to recognizing a wake-up word from a first audio segment at beginning of the target audio data; in which, the second audio segment is later than the first audio segment or has an overlapping portion with the first audio segment.