VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition

Quan Wang
Quan Wang
Mert Saglam
Mert Saglam
Alan Chiao
Alan Chiao
Renjie Liu
Renjie Liu
Yanzhang He
Yanzhang He
Wei Li
Wei Li
Jason Pelecanos
Jason Pelecanos
Marily Nika
Marily Nika

INTERSPEECH, pp. 2677-2681, 2020.

Cited by: 3|Views15
EI

Abstract:

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents numerous challenges: It should improve the performance when the input signal consists of overlapped spe...More

Code:

Data:

Your rating :
0

 

Tags
Comments