Saved in:
Bibliographic Details
Main Authors: Zhang, Yu, Tian, Baotong, Duan, Zhiyao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.14534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911131471183872
author Zhang, Yu
Tian, Baotong
Duan, Zhiyao
author_facet Zhang, Yu
Tian, Baotong
Duan, Zhiyao
contents Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these challenges, we introduce Conan, a chunkwise online zero-shot voice conversion model that preserves the content of the source while matching the voice timbre and styles of reference speech. Conan comprises three core components: 1) a Stream Content Extractor that leverages Emformer for low-latency streaming content encoding; 2) an Adaptive Style Encoder that extracts fine-grained stylistic features from reference speech for enhanced style adaptation; 3) a Causal Shuffle Vocoder that implements a fully causal HiFiGAN using a pixel-shuffle mechanism. Experimental evaluations demonstrate that Conan outperforms baseline models in subjective and objective metrics. Audio samples can be found at https://aaronz345.github.io/ConanDemo.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion
Zhang, Yu
Tian, Baotong
Duan, Zhiyao
Audio and Speech Processing
Computation and Language
Sound
Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these challenges, we introduce Conan, a chunkwise online zero-shot voice conversion model that preserves the content of the source while matching the voice timbre and styles of reference speech. Conan comprises three core components: 1) a Stream Content Extractor that leverages Emformer for low-latency streaming content encoding; 2) an Adaptive Style Encoder that extracts fine-grained stylistic features from reference speech for enhanced style adaptation; 3) a Causal Shuffle Vocoder that implements a fully causal HiFiGAN using a pixel-shuffle mechanism. Experimental evaluations demonstrate that Conan outperforms baseline models in subjective and objective metrics. Audio samples can be found at https://aaronz345.github.io/ConanDemo.
title Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2507.14534