Method and apparatus with model training and/or sequence recognition

A processor-implemented method includes: using an encoder, determining, for each of a plurality of tokens included in an input sequence, a self-attention weight based on a token and one or more tokens that precede the token in the input sequence; using the encoder, determining context information co...

Full description

Saved in:
Bibliographic Details
Main Author Lee, Hodong
Format Patent
LanguageEnglish
Published 11.10.2022
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
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 processor-implemented method includes: using an encoder, determining, for each of a plurality of tokens included in an input sequence, a self-attention weight based on a token and one or more tokens that precede the token in the input sequence; using the encoder, determining context information corresponding to the input sequence based on the determined self-attention weights; and using a decoder, determining an output sequence corresponding to the input sequence based on the determined context information.
Bibliography:Application Number: US202016831206