Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Ye-Xin, Du, Hui-Peng, Liu, Fei, Ai, Yang, Ling, Zhen-Hua
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features
by: Shi, Yu-Fei, et al.
Published: (2024)

DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis
by: Lu, Ye-Xin, et al.
Published: (2025)

BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation
by: Du, Hui-Peng, et al.
Published: (2024)

Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
by: Shi, Yu-Fei, et al.
Published: (2024)

ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
by: Jiang, Xiao-Hang, et al.
Published: (2024)

APCodec: A Neural Audio Codec with Parallel Amplitude and Phase Spectrum Encoding and Decoding
by: Ai, Yang, et al.
Published: (2024)

Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction
by: Lu, Ye-Xin, et al.
Published: (2024)

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
by: Lu, Ye-Xin, et al.
Published: (2023)

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
by: Gong, Cheng, et al.
Published: (2023)

Zero-shot Cross-lingual Voice Transfer for TTS
by: Biadsy, Fadi, et al.
Published: (2024)

StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
by: Chen, Zhiyong, et al.
Published: (2024)

Acoustic BPE for Speech Generation with Discrete Tokens
by: Shen, Feiyu, et al.
Published: (2023)

MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
by: Jiang, Xiao-Hang, et al.
Published: (2024)

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
by: Wang, Chunhui, et al.
Published: (2024)

APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm
by: Du, Hui-Peng, et al.
Published: (2024)

Stage-Wise and Prior-Aware Neural Speech Phase Prediction
by: Liu, Fei, et al.
Published: (2024)

Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control
by: Lu, Ye-Xin, et al.
Published: (2024)

VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
by: Peng, Puyuan, et al.
Published: (2025)

Universal Preference-Score-based Pairwise Speech Quality Assessment
by: Shi, Yu-Fei, et al.
Published: (2025)

DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness
by: Pankov, Vikentii, et al.
Published: (2023)

Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
by: Zheng, Rui-Chen, et al.
Published: (2025)

Low-Latency Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks
by: Ai, Yang, et al.
Published: (2024)

An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS
by: Kunešová, Marie, et al.
Published: (2025)

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
by: Eskimez, Sefik Emre, et al.
Published: (2024)

Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement
by: Chen, Qianniu, et al.
Published: (2025)

Vision-Integrated High-Quality Neural Speech Coding
by: Guo, Yao, et al.
Published: (2025)

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
by: Yao, Jixun, et al.
Published: (2025)

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
by: Kim, Jaehyeon, et al.
Published: (2024)

Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs
by: He, Xinlu, et al.
Published: (2025)

Intelli-Z: Toward Intelligible Zero-Shot TTS
by: Jung, Sunghee, et al.
Published: (2024)

Enhancing TTS Stability in Hebrew using Discrete Semantic Units
by: Zeldes, Ella, et al.
Published: (2024)

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
by: Jiang, Ziyue, et al.
Published: (2023)

Exploring the Benefits of Tokenization of Discrete Acoustic Units
by: Dekel, Avihu, et al.
Published: (2024)

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
by: Wang, Cong, et al.
Published: (2025)

Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations
by: Jeon, Yejin, et al.
Published: (2024)

WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language Understanding
by: Li, Mohan, et al.
Published: (2024)

HD-PPT: Hierarchical Decoding of Content- and Prompt-Preference Tokens for Instruction-based TTS
by: Nie, Sihang, et al.
Published: (2025)

Efficient Emotion and Speaker Adaptation in LLM-Based TTS via Characteristic-Specific Partial Fine-Tuning
by: Wang, Tianrui, et al.
Published: (2025)

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
by: Wang, Xinsheng, et al.
Published: (2025)

LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
by: Dang, Trung, et al.
Published: (2024)