Sign in

Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR

By Zelin Wu and others at
LogoGoogle
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data. Attention-based biasing is a leading approach which allows for full end-to-end cotraining of the recognizer and biasing system and requires no... Show more
April 23, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
Click on play to start listening