Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

Ethan A. Chi
Ethan A. Chi
Julian Salazar
Julian Salazar
Cited by: 0|Bibtex|Views4
Other Links: arxiv.org

Abstract:

Non-autoregressive models greatly improve decoding speed over typical sequence-to-sequence models, but suffer from degraded performance. Infilling and iterative refinement models make up some of this gap by editing the outputs of a non-autoregressive model, but are constrained in the edits that they can make. We propose iterative realig...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments