Adapter Finetuning with Teacher Pseudo-Labeling for Tail Languages in Streaming Multilingual ASR
Number of patents in Portfolio can not be more than 2000
United States of America
Stats
-
N/A
Issued Date -
Mar 6, 2025
app pub date -
Sep 6, 2024
filing date -
Sep 6, 2024
priority date (Note) -
Published
status (Latency Note)
Importance
Abstract
A method includes receiving a sequence of acoustic frames characterizing a spoken utterance in a particular native language. The method also includes generating a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames by a causal encoder that includes an initial stack of multi-head attention layers. The method also includes generating a second higher order feature representation for a corresponding first higher order feature representation by a non-causal encoder that includes a final stack of multi-head attention layers. The method also includes receiving, as input at each corresponding language-dependent adapter (LDA) module, a language ID vector identifying the particular native language to activate corresponding language-dependent weights specific to the particular native language. The method also includes generating a first probability distribution over possible speech recognition hypotheses by a decoder.
First Claim
Family
International Classification(s)
Cited Art Landscape
Patent Citation Ranking
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully