Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Qian, Graham, Calbert
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915123143114752
author Yang, Qian
Graham, Calbert
author_facet Yang, Qian
Graham, Calbert
contents Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significantly improves VC performance, reducing training costs while achieving high-quality voice conversion. The Stepback network's design offers a promising solution for advanced voice conversion tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15613
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning
Yang, Qian
Graham, Calbert
Sound
Computation and Language
Audio and Speech Processing
Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significantly improves VC performance, reducing training costs while achieving high-quality voice conversion. The Stepback network's design offers a promising solution for advanced voice conversion tasks.
title Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2501.15613