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

facebooktwittermailshare

DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS

Abstract: 

Deep neural networks (DNNs) have been successfully deployed for acoustic modelling in statistical parametric speech synthesis (SPSS) systems. Moreover, DNN-based postfilters (PF) have also been shown to outperform conventional postfilters that are widely used in SPSS systems for increasing the quality of synthesized speech. However, existing DNN-based postfilters are trained with speaker-dependent databases. Given that SPSS systems can rapidly adapt to new speakers from generic models, there is a need for DNN-based postfilters that can adapt to new speakers with minimal adaptation data. Here, we compare DNN-, RNN-, and CNN-based postfilters together with adversarial (GAN) training and cluster-based initialization (CI) for rapid adaptation. Results indicate that the feedforward (FF) DNN, together with GAN and CI, significantly outperforms the other recently proposed postfilters.

up
0 users have voted:

Paper Details

Authors:
Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu
Submitted On:
10 May 2019 - 7:36am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Cenk Demiroglu
Paper Code:
ICASSP19005
Document Year:
2019
Cite

Document Files

ICASSP_2019_v1.pptx

(54)

Subscribe

[1] Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu, "DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4306. Accessed: Feb. 27, 2020.
@article{4306-19,
url = {http://sigport.org/4306},
author = {Miraç Göksu Öztürk; Okan Ulusoy; Cenk Demiroglu },
publisher = {IEEE SigPort},
title = {DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS},
year = {2019} }
TY - EJOUR
T1 - DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS
AU - Miraç Göksu Öztürk; Okan Ulusoy; Cenk Demiroglu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4306
ER -
Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu. (2019). DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS. IEEE SigPort. http://sigport.org/4306
Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu, 2019. DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS. Available at: http://sigport.org/4306.
Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu. (2019). "DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS." Web.
1. Miraç Göksu Öztürk, Okan Ulusoy, Cenk Demiroglu. DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4306