DINO-VITS: Data-efficient Zero-shot TTS With Self-supervised Speaker Verification Loss For Noise Robustness
2023 · Vikentii Pankov, Valeria Pronina, Alexander Kuzmin, et al.
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.
Authors
(none)
Tags
Stats
Related papers
- Self-supervised Learning With Cluster-aware-dino For High-performance Robust Speaker Verification (2023)0.00
- Pushing The Limits Of Self-supervised Speaker Verification Using Regularized Distillation Framework (2022)17.00
- Textless Acoustic Model With Self-supervised Distillation For Noise-robust Expressive Speech-to-speech Translation (2024)3.58
- Noise-robust Zero-shot Text-to-speech Synthesis Conditioned On Self-supervised Speech-representation Model With Adapters (2024)7.50
- An Investigation Of Noise Robustness For Flow-matching-based Zero-shot TTS (2024)5.24
- Enhancing Zero-shot Multi-speaker TTS With Negated Speaker Representations (2024)3.58
- Robust Disentangled Variational Speech Representation Learning For Zero-shot Voice Conversion (2022)10.97
- Feature Enhancement With Deep Feature Losses For Speaker Verification (2019)10.61