DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness

Vikentii Pankov, Valeria Pronina, Alexander Kuzmin +7

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 th…