Saved in:
Bibliographic Details
Main Authors: Yang, Haoyuan, Yang, Mu, Xie, Jiamin, Chen, Szu-Jui, Hansen, John H. L.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911501135118336
author Yang, Haoyuan
Yang, Mu
Xie, Jiamin
Chen, Szu-Jui
Hansen, John H. L.
author_facet Yang, Haoyuan
Yang, Mu
Xie, Jiamin
Chen, Szu-Jui
Hansen, John H. L.
contents Recent advances in zero-shot voice conversion have exhibited potential in emotion control, yet the performance is suboptimal or inconsistent due to their limited expressive capacity. We propose Emotion-Aware Prefix for explicit emotion control in a two-stage voice conversion backbone. We significantly improve emotion conversion performance, doubling the baseline Emotion Conversion Accuracy (ECA) from 42.40% to 85.50% while maintaining linguistic integrity and speech quality, without compromising speaker identity. Our ablation study suggests that a joint control of both sequence modulation and acoustic realization is essential to synthesize distinct emotions. Furthermore, comparative analysis verifies the generalizability of proposed method, while it provides insights on the role of acoustic decoupling in maintaining speaker identity.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09120
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Emotion-Aware Prefix: Towards Explicit Emotion Control in Voice Conversion Models
Yang, Haoyuan
Yang, Mu
Xie, Jiamin
Chen, Szu-Jui
Hansen, John H. L.
Audio and Speech Processing
Recent advances in zero-shot voice conversion have exhibited potential in emotion control, yet the performance is suboptimal or inconsistent due to their limited expressive capacity. We propose Emotion-Aware Prefix for explicit emotion control in a two-stage voice conversion backbone. We significantly improve emotion conversion performance, doubling the baseline Emotion Conversion Accuracy (ECA) from 42.40% to 85.50% while maintaining linguistic integrity and speech quality, without compromising speaker identity. Our ablation study suggests that a joint control of both sequence modulation and acoustic realization is essential to synthesize distinct emotions. Furthermore, comparative analysis verifies the generalizability of proposed method, while it provides insights on the role of acoustic decoupling in maintaining speaker identity.
title Emotion-Aware Prefix: Towards Explicit Emotion Control in Voice Conversion Models
topic Audio and Speech Processing
url https://arxiv.org/abs/2603.09120