The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge

TL;DR

This paper introduces a multi-lingual, multi-speaker few-shot voice cloning system that enhances speaker similarity and naturalness through novel model components and data strategies, achieving top MOS scores in the LIMMITS'24 Challenge.

Contribution

We develop a multi-speaker multi-lingual few-shot voice cloning system with speaker-aware encoding, flow-based decoding, and advanced data augmentation techniques, outperforming existing methods.

Findings

Achieved a speaker similarity MOS of 4.25.

Obtained a naturalness MOS of 3.97.

Performed well in the 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.