SPEECHSPLIT2.0: UNSUPERVISED SPEECH DISENTANGLEMENT FOR VOICE CONVERSION WITHOUT TUNING AUTOENCODER BOTTLENECKS

Chak Ho Chan, Kaizhi Qian, Yang Zhang, Mark Hasegawa-Johnson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

SPEECHSPLIT can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner. However, SPEECHSPLIT requires careful tuning of the autoencoder bottlenecks, which can be time-consuming and less robust. This paper proposes SPEECHSPLIT2.0, which constrains the information flow of the speech component to be disentangled on the autoencoder input using efficient signal processing methods instead of bottleneck tuning. Evaluation results show that SPEECHSPLIT2.0 achieves comparable performance to SPEECHSPLIT in speech disentanglement and superior robustness to the bottleneck size variations. Our code is available at https://github.com/biggytruck/SpeechSplit2.

Original languageEnglish (US)
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5243-5247
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: May 23 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period5/23/225/27/22

Keywords

  • Speech Disentanglement
  • Unsupervised Learning
  • Voice Conversion

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this