METHOD AND APPARATUS FOR PERFORMING RECOGNITION USING RECURRENT MODEL AND TRAINING RECURRENT MODEL

A recognition method includes extracting target data corresponding to a current window and padding data subsequent to the target data from sequence data; acquiring a state parameter corresponding to a previous window; and calculating a recognition result for the current window based on the state par...

Full description

Saved in:
Bibliographic Details
Main Author Yoo, Sang Hyun
Format Patent
LanguageEnglish
French
German
Published 16.03.2022
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
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:A recognition method includes extracting target data corresponding to a current window and padding data subsequent to the target data from sequence data; acquiring a state parameter corresponding to a previous window; and calculating a recognition result for the current window based on the state parameter, the extracted target data, and the extracted padding data using a recurrent model.
Bibliography:Application Number: EP20170190423