The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge
Abstract
This paper presents the multi-speaker multi-lingual few-shot voice cloning system developed by THU-HCSI team for LIMMITS'24 Challenge. To achieve high speaker similarity and naturalness in both mono-lingual and cross-lingual scenarios, we build the system upon YourTTS and add several enhancements. For further improving speaker similarity and speech quality, we introduce speaker-aware text encoder and flow-based decoder with Transformer blocks. In addition, we denoise the few-shot data, mix up them with pre-training data, and adopt a speaker-balanced sampling strategy to guarantee effective fine-tuning for target speakers. The official evaluations in track 1 show that our system achieves the best speaker similarity MOS of 4.25 and obtains considerable naturalness MOS of 3.97.
Cite
@article{arxiv.2404.16619,
title = {The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge},
author = {Yixuan Zhou and Shuoyi Zhou and Shun Lei and Zhiyong Wu and Menglin Wu},
journal= {arXiv preprint arXiv:2404.16619},
year = {2024}
}
Comments
Accepted in Grand Challenge of ICASSP 2024