Speech recognition method and device, electronic equipment and storage medium

The invention relates to the field of voice recognition, in particular to a voice recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a current to-be-processed data frame and a context to-be-processed data frame of the current to-be...

Full description

Saved in:
Bibliographic Details
Main Author BAN ZHIHUA
Format Patent
LanguageChinese
English
Published 10.05.2024
Subjects
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:The invention relates to the field of voice recognition, in particular to a voice recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a current to-be-processed data frame and a context to-be-processed data frame of the current to-be-processed data frame, the context to-be-processed data frame comprises a previous to-be-processed data frame before the current to-be-processed data frame and a next to-be-processed data frame after the current to-be-processed data frame; on the basis of the context to-be-processed data frame, performing preprocessing of increasing a receptive field on the current to-be-processed data frame to obtain a preprocessing result of the current to-be-processed data frame; and according to the pre-processing result, coding and decoding after coding are carried out, and a speech recognition result is determined. Before coding, the context to-be-processed data frame is utilized to perform the preprocessing of increasing the
Bibliography:Application Number: CN202211391374