Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Ye-Xin, Du, Hui-Peng, Liu, Fei, Ai, Yang, Ling, Zhen-Hua
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915297643986944
author Lu, Ye-Xin
Du, Hui-Peng
Liu, Fei
Ai, Yang
Ling, Zhen-Hua
author_facet Lu, Ye-Xin
Du, Hui-Peng
Liu, Fei
Ai, Yang
Ling, Zhen-Hua
contents Large language model (LLM) based zero-shot text-to-speech (TTS) methods tend to preserve the acoustic environment of the audio prompt, leading to degradation in synthesized speech quality when the audio prompt contains noise. In this paper, we propose a novel neural codec-based speech denoiser and integrate it with the advanced LLM-based TTS model, LauraTTS, to achieve noise-robust zero-shot TTS. The proposed codec denoiser consists of an audio codec, a token denoiser, and an embedding refiner. The token denoiser predicts the first two groups of clean acoustic tokens from the noisy ones, which can serve as the acoustic prompt for LauraTTS to synthesize high-quality personalized speech or be converted to clean speech waveforms through the embedding refiner and codec decoder. Experimental results show that our proposed codec denoiser outperforms state-of-the-art speech enhancement (SE) methods, and the proposed noise-robust LauraTTS surpasses the approach using additional SE models.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
Lu, Ye-Xin
Du, Hui-Peng
Liu, Fei
Ai, Yang
Ling, Zhen-Hua
Audio and Speech Processing
Sound
Large language model (LLM) based zero-shot text-to-speech (TTS) methods tend to preserve the acoustic environment of the audio prompt, leading to degradation in synthesized speech quality when the audio prompt contains noise. In this paper, we propose a novel neural codec-based speech denoiser and integrate it with the advanced LLM-based TTS model, LauraTTS, to achieve noise-robust zero-shot TTS. The proposed codec denoiser consists of an audio codec, a token denoiser, and an embedding refiner. The token denoiser predicts the first two groups of clean acoustic tokens from the noisy ones, which can serve as the acoustic prompt for LauraTTS to synthesize high-quality personalized speech or be converted to clean speech waveforms through the embedding refiner and codec decoder. Experimental results show that our proposed codec denoiser outperforms state-of-the-art speech enhancement (SE) methods, and the proposed noise-robust LauraTTS surpasses the approach using additional SE models.
title Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2505.13830