公开(公告)号：US12112746B2

公开(公告)日：2024-10-08

申请号：US17476333

申请日：2021-09-15

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Jinfeng Bai ,  Zhijian Wang ,  Cong Gao

IPC: G10L15/22

CPC classification number: G10L15/22 ,  G10L2015/223

Abstract: The present disclosure provides a method and a device for processing voice interaction, an electronic device and a storage medium. The method includes: determining a first integrity of a voice instruction from a user by using a pre-trained integrity detection model in response to detecting that the voice instruction from the user is not a high-frequency instruction; determining a waiting duration for the voice instruction based on the first integrity and a preset integrity threshold, wherein the waiting duration for the voice instruction indicates a length of period between a time when a voice interaction device determines that receiving the voice instruction is completed and a time when the voice interaction device performs an operation in response to the voice instruction of the user; and controlling the voice interaction device to respond to the voice instruction of the user based on the waiting duration.

公开(公告)号：US11893977B2

公开(公告)日：2024-02-06

申请号：US17530276

申请日：2021-11-18

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

Inventor： Zhijian Wang ,  Sheng Qian ,  Qi Zhang

IPC: G10L15/183 ,  G10L15/00 ,  G10L15/32

CPC classification number: G10L15/005 ,  G10L15/183 ,  G10L15/32

Abstract: A method for recognizing a Chinese-English mixed speech, includes: determining pronunciation information and scores of a language model, of speech information, in response to receiving the speech information; determining whether an English word exists in content of the speech information based on the pronunciation information; determining a Chinese word corresponding to the English word based on a preset Chinese-English mapping table in response to the English word existing in the content of the speech information, in which the Chinese-English mapping table includes a mapping relationship of at least one pair of English word and Chinese word; determining a score of the Chinese word corresponding to the English word; replacing a score of the English word in the scores of the language model with the score of the Chinese word; and obtaining a speech recognition result for the speech information based on the replaced scores of the language model.

公开(公告)号：US20220068267A1

公开(公告)日：2022-03-03

申请号：US17451033

申请日：2021-10-15

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

Inventor： Zhen Wu ,  Maoren Zhou ,  Zhijian Wang ,  Yafeng Cui ,  Yufang Wu ,  Qin Qu ,  Bing Liu ,  Jiaxiang Ge

IPC: G10L15/18 ,  G10L15/08 ,  G10L15/02

Abstract: The disclosure provides a method and an apparatus for recognizing a speech, an electronic device and a storage medium. Based on obtaining target speech information, state information of an application corresponding to the target speech information and contextual information are obtained. Semantic completeness of the target speech information is obtained based on the state information and the contextual information. A monitoring duration corresponding to the semantic completeness is obtained, and it is monitored whether there is speech information within the monitoring duration. Speech recognition is performed on the target speech information based on no speech information being monitored within the monitoring duration.