A codec-token denoiser that predicts only the first two token groups of clean audio enables noise-robust zero-shot TTS, matching clean-prompt performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
A codec-token denoiser that predicts only the first two token groups of clean audio enables noise-robust zero-shot TTS, matching clean-prompt performance.