FurcaNeXt: End-to-End Monaural Speech Separation with Dynamic Gated Dilated Temporal Convolutional Networks

Liwen Zhang
Liwen Zhang
Ziqiang Shi
Ziqiang Shi
Anyan Shi
Anyan Shi
Ding Ma
Ding Ma

MMM (1), pp. 653-665, 2020.

Cited by: 13|Bibtex|Views10|Links
EI

Abstract:

Deep dilated temporal convolutional networks (TCN) have been proved to be very effective in sequence modeling. In this paper we propose several improvements of TCN for end-to-end approach to monaural speech separation, which consists of (1) multi-scale dynamic weighted gated TCN with a pyramidal structure (FurcaPy), (2) gated TCN with int...More

Code:

Data:

Your rating :
0

 

Tags
Comments