公开(公告)号：US12183323B2

公开(公告)日：2024-12-31

申请号：US17644749

申请日：2021-12-16

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

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

IPC: G10L15/02 ,  G10L15/16 ,  G10L19/032

Abstract: The present disclosure provides a method of recognizing speech offline, electronic device, and a storage medium, relating to a field of artificial intelligence such as speech recognition, natural language processing, and deep learning. The method may include: decoding speech data to be recognized into a syllable recognition result; transforming the syllable recognition result into a corresponding text as a speech recognition result of the speech data.

公开(公告)号：US12067970B2

公开(公告)日：2024-08-20

申请号：US17500188

申请日：2021-10-13

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

Inventor： Jiaxiang Ge ,  Zhen Wu ,  Maoren Zhou ,  Qiguang Zang ,  Ming Wen ,  Xiaoyin Fu

IPC: G10L15/02 ,  G10L15/06 ,  G10L15/20 ,  G10L15/22

CPC classification number: G10L15/02 ,  G10L15/063 ,  G10L15/20 ,  G10L15/22

Abstract: A method for mining feature information, an apparatus for mining feature information and an electronic device are disclosed. The method includes: determining a usage scenario of a target device; obtaining raw audio data including real scenario data, speech synthesis data, recorded audio data and other media data; generating target audio data of the usage scenario by simulating the usage scenario based on the raw audio data; and obtaining feature information of the usage scenario by performing feature extraction on the target audio data.

公开(公告)号：US12033616B2

公开(公告)日：2024-07-09

申请号：US17571805

申请日：2022-01-10

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

Inventor： Junyao Shao ,  Xiaoyin Fu ,  Qiguang Zang ,  Zhijie Chen ,  Mingxin Liang ,  Huanxin Zheng ,  Sheng Qian

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G10L15/28

CPC classification number: G10L15/063 ,  G10L15/16 ,  G10L15/183 ,  G10L15/28

Abstract: A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.