Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Speaker-dependent WaveNet-based delay-free ADPCM speech coding

Abstract: 

This paper proposes a WaveNet-based delay-free adaptive differential pulse code modulation (ADPCM) speech coding system. The WaveNet generative model, which is a stateof-the-art model for neural-network-based speech waveform synthesis, is used as the adaptive predictor in ADPCM. To further improve speech quality, mel-cepstrum-based noise shaping and postfiltering were integrated with the proposed ADPCM system. Both objective and subjective evaluation results indicate that the proposed ADPCM system outperformed not only the conventional ADPCM system based on ITU-T Recommendation G.726 but also the ADPCM system based on adaptive mel-cepstral analysis.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
7 May 2019 - 10:45pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Takenori Yoshimura
Document Year:
2019
Cite

Document Files

poster.pdf

(46)

Keywords

Subscribe

[1] , "Speaker-dependent WaveNet-based delay-free ADPCM speech coding", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3996. Accessed: Nov. 20, 2019.
@article{3996-19,
url = {http://sigport.org/3996},
author = { },
publisher = {IEEE SigPort},
title = {Speaker-dependent WaveNet-based delay-free ADPCM speech coding},
year = {2019} }
TY - EJOUR
T1 - Speaker-dependent WaveNet-based delay-free ADPCM speech coding
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3996
ER -
. (2019). Speaker-dependent WaveNet-based delay-free ADPCM speech coding. IEEE SigPort. http://sigport.org/3996
, 2019. Speaker-dependent WaveNet-based delay-free ADPCM speech coding. Available at: http://sigport.org/3996.
. (2019). "Speaker-dependent WaveNet-based delay-free ADPCM speech coding." Web.
1. . Speaker-dependent WaveNet-based delay-free ADPCM speech coding [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3996