公开(公告)号：US20210398022A1

公开(公告)日：2021-12-23

申请号：US17463748

申请日：2021-09-01

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

Inventor： Guibin WANG ,  Yangkai XU ,  Huanxin ZHENG ,  Yue GUO

IPC: G06N20/00

Abstract: The present disclosure provides a method and apparatus of fusing operators, an electronic device and a storage medium, which relates to fields of deep learning, artificial intelligence and knowledge graph. The method includes: determining operator groups to be fused, according to an operator graph to be processed, wherein each operator group of the operator groups includes at least two operators in the operator graph respectively; obtaining a fused operator corresponding to the each operator group respectively; and for the fused operator, replacing corresponding operators in the operator graph with the fused operator respectively, and coupling dependence edges of the corresponding operators to the any fused operator, wherein the corresponding operators include operators in the operator group corresponding to the fused operator.

公开(公告)号：US20230410794A1

公开(公告)日：2023-12-21

申请号：US18237976

申请日：2023-08-25

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

Inventor： Xiaoyin FU ,  Mingshun YANG ,  Qiguang ZANG ,  Zhijie CHEN ,  Yangkai XU ,  Guibin WANG ,  Lei JIA

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/26

CPC classification number: G10L15/063 ,  G10L15/26 ,  G10L15/02

Abstract: An audio recognition method, a method of training an audio recognition model, and an electronic device are provided, which relate to fields of artificial intelligence, speech recognition, deep learning and natural language processing technologies. The audio recognition method includes: truncating an audio feature of target audio data to obtain at least one first audio sequence feature corresponding to a predetermined duration; obtaining, according to a peak information of the audio feature, a peak sub-information corresponding to the first audio sequence feature; performing at least one decoding operation on the first audio sequence feature to obtain a recognition result for the first audio sequence feature, a number of times the decoding operation is performed being identical to a number of peaks corresponding to the first audio sequence feature; obtaining target text data for the target audio data according to the recognition result for the at least one first audio sequence feature.

公开(公告)号：US20230177326A1

公开(公告)日：2023-06-08

申请号：US17968688

申请日：2022-10-18

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

Inventor： Guibin WANG ,  Shijun CONG ,  Hao DONG ,  Lei JIA

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454

Abstract: A technical solution for compressing a neural network model which relates to the field of artificial intelligence technologies, such as deep learning technologies, cloud service technologies, is disclosed. The method for compressing a neural network model includes: acquiring a to-be-compressed neural network model; determining a first bit width, a second bit width and a target thinning rate corresponding to the to-be-compressed neural network model; obtaining a target value according to the first bit width, the second bit width and the target thinning rate; and compressing the to-be-compressed neural network model using the target value, the first bit width and the second bit width to obtain a compression result of the to-be-compressed neural network model.