DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness
Abstract
We address zero-shot TTS systems' noise-robustness problem by proposing a dual-objective training for the speaker encoder using self-supervised DINO loss. This approach enhances the speaker encoder with the speech synthesis objective, capturing a wider range of speech characteristics beneficial for voice cloning. At the same time, the DINO objective improves speaker representation learning, ensuring robustness to noise and speaker discriminability. Experiments demonstrate significant improvements in subjective metrics under both clean and noisy conditions, outperforming traditional speaker-encoderbased TTS systems. Additionally, we explore training zeroshot TTS on noisy, unlabeled data. Our two-stage training strategy, leveraging self-supervised speech models to distinguish between noisy and clean speech, shows notable advances in similarity and naturalness, especially with noisy training datasets, compared to the ASR-transcription-based approach.
Cite
@article{arxiv.2311.09770,
title = {DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness},
author = {Vikentii Pankov and Valeria Pronina and Alexander Kuzmin and Maksim Borisov and Nikita Usoltsev and Xingshan Zeng and Alexander Golubkov and Nikolai Ermolenko and Aleksandra Shirshova and Yulia Matveeva},
journal= {arXiv preprint arXiv:2311.09770},
year = {2024}
}
Comments
Accepted to Interspeech2024