# An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS

arXiv: https://arxiv.org/abs/2406.05699 · HTML: https://mlsanity.com/paper/2406.05699/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)
- [A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI](https://mlsanity.com/paper/2303.13336/) (2023)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [Generative Pre-training for Speech with Flow Matching](https://mlsanity.com/paper/2310.16338/) (2023)
- [Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias](https://mlsanity.com/paper/2306.03509/) (2023)
- [E3 TTS: Easy End-to-End Diffusion-based Text to Speech](https://mlsanity.com/paper/2311.00945/) (2023)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like](https://mlsanity.com/paper/2402.07383/) (2024)
- [Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement](https://mlsanity.com/paper/2106.02896/) (2021)
- [Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters](https://mlsanity.com/paper/2401.05111/) (2024)
- [Real-Time Joint Personalized Speech Enhancement and Acoustic Echo Cancellation](https://mlsanity.com/paper/2211.02773/) (2022)

## Built on by (most cited first, 4 of 4)

- [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://mlsanity.com/paper/2604.00688/) (2026)
- [Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2407.12229/) (2024)
- [High-Order Matching for One-Step Shortcut Diffusion Models](https://mlsanity.com/paper/2502.00688/) (2025)
- [Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling](https://mlsanity.com/paper/2608.03011/) (2026)

## Abstract (arXiv)

Recently, zero-shot text-to-speech (TTS) systems, capable of synthesizing any speaker's voice from a short audio prompt, have made rapid advancements. However, the quality of the generated speech significantly deteriorates when the audio prompt contains noise, and limited research has been conducted to address this issue. In this paper, we explored various strategies to enhance the quality of audio generated from noisy audio prompts within the context of flow-matching-based zero-shot TTS. Our investigation includes comprehensive training strategies: unsupervised pre-training with masked speech denoising, multi-speaker detection and DNSMOS-based data filtering on the pre-training data, and fine-tuning with random noise mixing. The results of our experiments demonstrate significant improvements in intelligibility, speaker similarity, and overall audio quality compared to the approach of applying speech enhancement to the audio prompt.