vix.ing · top · new · best · stats · spec

SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks

2022/03/26 by Chak Ho Chan, Chan, Chak Ho, Kaizhi Qian +4 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2203.14156

openalex publication_date 2022/03/26 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28

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 SpeechSplit 2.0, 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 SpeechSplit 2.0 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.

Cited by

Related