A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

ICASSP, pp. 6059-6063, 2020.

Cited by: 52|Views118
EI

Abstract:

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) mode...More

Code:

Data:

Your rating :
0

 

Tags
Comments