VoiceGuider: Enhancing Out-of-Domain Performance in Parameter-Efficient Speaker-Adaptive Text-to-Speech via Autoguidance
Jiheum Yeom, Heeseung Kim, Jooyoung Choi, Che Hyun Lee, Nohil Park, Sungroh Yoon
Abstract
When applying parameter-efficient finetuning via LoRA onto speaker adaptive text-to-speech models, adaptation performance may decline compared to full-finetuned counterparts, especially for out-of-domain speakers. Here, we propose VoiceGuider, a parameter-efficient speaker adaptive text-to-speech system reinforced with autoguidance to enhance the speaker adaptation performance, reducing the gap against full-finetuned models. We carefully explore various ways of strengthening autoguidance, ultimately finding the optimal strategy. VoiceGuider as a result shows robust adaptation performance especially on extreme out-of-domain speech data. We provide audible samples in our demo page.
BibTeX
@inproceedings{icassp2025_voiceguiderenhan,
title = {VoiceGuider: Enhancing Out-of-Domain Performance in Parameter-Efficient Speaker-Adaptive Text-to-Speech via Autoguidance},
author = {Jiheum Yeom and Heeseung Kim and Jooyoung Choi and Che Hyun Lee and Nohil Park and Sungroh Yoon},
booktitle = {ICASSP 2025},
year = {2025}
}