Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions 论文

2020引用 279
DOI
Speech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
Speech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
相关技术:Music and Audio ProcessingSpeech and Audio ProcessingSpeech Recognition and Synthesis
关系图谱

Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions · 作者

J

Jason Li

R

R. Bret Leary

V

Vitaly Lavrukhin

O

Oleksii Kuchaiev

J

Jocelyn Huang

B

Boris Ginsburg

S

Stanislav Beliaev

S

Samuel Kriman