PHONEME-BASED CONTEXTUALIZATION FOR CROSS-LINGUAL SPEECH RECOGNITION IN END-TO-END MODELS

A method includes receiving audio data encoding an utterance spoken by a native speaker of a first language, and receiving a biasing term list including one or more terms in a second language different than the first language. The method also includes processing, using a speech recognition model, ac...

Full description

Saved in:
Bibliographic Details
Main Authors Bruguier, Antoine Jean, Hu, Ke, Pundak, Golan, Sainath, Tara N, Prabhavalkar, Rohit Prakash
Format Patent
LanguageEnglish
Published 02.06.2022
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:A method includes receiving audio data encoding an utterance spoken by a native speaker of a first language, and receiving a biasing term list including one or more terms in a second language different than the first language. The method also includes processing, using a speech recognition model, acoustic features derived from the audio data to generate speech recognition scores for both wordpieces and corresponding phoneme sequences in the first language. The method also includes rescoring the speech recognition scores for the phoneme sequences based on the one or more terms in the biasing term list, and executing, using the speech recognition scores for the wordpieces and the rescored speech recognition scores for the phoneme sequences, a decoding graph to generate a transcription for the utterance.
Bibliography:Application Number: US202217651315