Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Yu, Yang, Yuguang, Yao, Jixun, Ma, Lei, Zhao, Jianjun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909729807138816
author Pan, Yu
Yang, Yuguang
Yao, Jixun
Ma, Lei
Zhao, Jianjun
author_facet Pan, Yu
Yang, Yuguang
Yao, Jixun
Ma, Lei
Zhao, Jianjun
contents Despite recent advances in zero-shot voice conversion (VC), achieving speaker similarity and naturalness comparable to ground-truth recordings remains a significant challenge. In this letter, we propose CTEFM-VC, a zero-shot VC framework that integrates content-aware timbre ensemble modeling with conditional flow matching. Specifically, CTEFM-VC decouples utterances into content and timbre representations and leverages a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. To enhance its timbre modeling capability and naturalness of generated speech, we first introduce a context-aware timbre ensemble modeling approach that adaptively integrates diverse speaker verification embeddings and enables the effective utilization of source content and target timbre elements through a cross-attention module. Furthermore, a structural similarity-based timbre loss is presented to jointly train CTEFM-VC end-to-end. Experiments show that CTEFM-VC consistently achieves the best performance in all metrics assessing speaker similarity, speech naturalness, and intelligibility, significantly outperforming state-of-the-art zero-shot VC systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02026
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching
Pan, Yu
Yang, Yuguang
Yao, Jixun
Ma, Lei
Zhao, Jianjun
Sound
Artificial Intelligence
Audio and Speech Processing
Despite recent advances in zero-shot voice conversion (VC), achieving speaker similarity and naturalness comparable to ground-truth recordings remains a significant challenge. In this letter, we propose CTEFM-VC, a zero-shot VC framework that integrates content-aware timbre ensemble modeling with conditional flow matching. Specifically, CTEFM-VC decouples utterances into content and timbre representations and leverages a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. To enhance its timbre modeling capability and naturalness of generated speech, we first introduce a context-aware timbre ensemble modeling approach that adaptively integrates diverse speaker verification embeddings and enables the effective utilization of source content and target timbre elements through a cross-attention module. Furthermore, a structural similarity-based timbre loss is presented to jointly train CTEFM-VC end-to-end. Experiments show that CTEFM-VC consistently achieves the best performance in all metrics assessing speaker similarity, speech naturalness, and intelligibility, significantly outperforming state-of-the-art zero-shot VC systems.
title Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2411.02026