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

facebooktwittermailshare

Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks

Abstract: 

The present paper describes singing voice synthesis based on convolutional neural networks (CNNs). Singing voice synthesis systems based on deep neural networks (DNNs) are currently being proposed and are improving the naturalness of synthesized singing voices. As singing voices represent a rich form of expression, a powerful technique to model them accurately is required. In the proposed technique, long-term dependencies of singing voices are modeled by CNNs. An acoustic feature sequence is generated for each segment that consists of long-term frames, and a natural trajectory is obtained without the parameter generation algorithm. Furthermore, a computational complexity reduction technique, which drives the DNNs in different time units depending on type of musical score features, is proposed. Experimental results show that the proposed method can synthesize natural sounding singing voices much faster than the conventional method.

up
0 users have voted:

Paper Details

Authors:
Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
Submitted On:
20 May 2020 - 8:26pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Kazuhiro Nakamura
Paper Code:
SPE-P12.8
Document Year:
2020
Cite

Document Files

ICASSP2020_slide_20200417b.pdf

(42)

Subscribe

[1] Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, "Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5421. Accessed: Sep. 23, 2020.
@article{5421-20,
url = {http://sigport.org/5421},
author = {Kazuhiro Nakamura; Shinji Takaki; Kei Hashimoto; Keiichiro Oura; Yoshihiko Nankaku; Keiichi Tokuda },
publisher = {IEEE SigPort},
title = {Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks},
year = {2020} }
TY - EJOUR
T1 - Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
AU - Kazuhiro Nakamura; Shinji Takaki; Kei Hashimoto; Keiichiro Oura; Yoshihiko Nankaku; Keiichi Tokuda
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5421
ER -
Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda. (2020). Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks. IEEE SigPort. http://sigport.org/5421
Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, 2020. Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks. Available at: http://sigport.org/5421.
Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda. (2020). "Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks." Web.
1. Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda. Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5421