公开(公告)号：US20240221727A1

公开(公告)日：2024-07-04

申请号：US18266432

申请日：2022-09-01

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

Inventor： Lanhua YOU ,  Lei JIA ,  Qi ZHANG ,  Zhengxiang JIANG

IPC: G10L15/06 ,  G10L15/01 ,  G10L15/02 ,  G10L15/16

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/02 ,  G10L15/16

Abstract: The present disclosure provides a voice recognition model training method and apparatus, an electronic device and a storage medium, relating to the field of artificial intelligence technology, and in particular to the fields such as deep learning and voice recognition. The specific implementation scheme includes constructing a negative sample according to a positive sample to obtain a target negative sample for constraining a voice decoding path; obtaining training data according to the positive sample and the target negative sample; and training a first voice recognition model according to the training data to obtain a second voice recognition model.

公开(公告)号：US20220139369A1

公开(公告)日：2022-05-05

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: G10L15/00 ,  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：US20220245764A1

公开(公告)日：2022-08-04

申请号：US17723201

申请日：2022-04-18

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

Inventor： Qi ZHANG ,  Kangyi ZHI

IPC: G06T3/40 ,  G06N3/08

Abstract: A method for an image super-solution, a device and a storage medium are provided. The method may include: acquiring training samples, where the training samples include a first-resolution sample image and a corresponding second-resolution sample image, and a resolution of the second-resolution sample image is N times a resolution of the sample of first resolution, N being a positive integer; and training an initial network model by using the first-resolution sample image as an input and using the second-resolution sample image as an output, to obtain the super-resolution model.

公开(公告)号：US20220108684A1

公开(公告)日：2022-04-07

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：US20230011823A1

公开(公告)日：2023-01-12

申请号：US17939401

申请日：2022-09-07

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd

Inventor： Qi ZHANG ,  Weidong Hu

IPC: G06T5/00 ,  G06V10/42 ,  G06V10/44 ,  G06V10/80

Abstract: The present disclosure provides a method and apparatus for converting an image format, an electronic device, a computer readable storage medium and a computer program product, relates to the field of artificial intelligence technology such as computer vision and deep learning, and can be applied to intelligent sensing ultra-definition scenarios. A specific implementation of the method includes: acquiring a to-be-converted standard dynamic range image; performing a convolution operation on the standard dynamic range image to obtain a local feature; performing a global average pooling operation on the standard dynamic range image to obtain a global feature; and converting the standard dynamic range image into a high dynamic range image according to the local feature and the global feature.