FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Jiahui Yu
Jiahui Yu
Shuo-yiin Chang
Shuo-yiin Chang
Wei Han
Wei Han
Anmol Gulati
Anmol Gulati
Cited by: 0|Bibtex|Views22
Other Links: arxiv.org

Abstract:

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches including Early and Late Penalties and Constrained Alignments penalize emission delay b...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments