A Better and Faster End-to-End Model for Streaming ASR

Anmol Gulati
Anmol Gulati
Jiahui Yu
Jiahui Yu
Shuo-Yiin Chang
Shuo-Yiin Chang
James Qin
James Qin
Qiao Liang
Qiao Liang
Cited by: 0|Bibtex|Views22
Other Links: arxiv.org

Abstract:

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However, the model still tends to delay the predictions towards the end and thus has much higher partial l...More

Code:

Data:

Your rating :
0

 

Tags
Comments