F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been proposed. Recently, AU-TOVC, a conditional autoencoders (CAEs) b...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 6284 - 6288
Main Authors: Qian, Kaizhi, Jin, Zeyu, Hasegawa-Johnson, Mark, Mysore, Gautham J.
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2020
Subjects:
Acoustics
autoencoder
Conferences
F0-conversion
Generative adversarial networks
Signal processing
Speech processing
Task analysis
Tuning
voice-conversion
WaveNet-vocoder
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been proposed. Recently, AU-TOVC, a conditional autoencoders (CAEs) based method achieved state-of-the-art results by disentangling the speaker identity and speech content using information-constraining bottlenecks, and it achieves zero-shot conversion by swapping in a different speaker's identity embedding to synthesize a new voice. However, we found that while speaker identity is disentangled from speech content, a significant amount of prosodic information, such as source F0, leaks through the bottleneck, causing target F0 to fluctuate unnaturally. Furthermore, AutoVC has no control of the converted F0 and thus unsuitable for many applications. In the paper, we modified and improved autoencoder-based voice conversion to disentangle content, F0, and speaker identity at the same time. Therefore, we can control the F0 contour, generate speech with F0 consistent with the target speaker, and significantly improve quality and similarity. We support our improvement through quantitative and qualitative analysis.
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9054734