# Traceable TTS: Toward Watermark-Free TTS with Strong Traceability

arXiv: https://arxiv.org/abs/2507.03887 · HTML: https://mlsanity.com/paper/2507.03887/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 5 Jul 2025.

## Builds on (most cited first, 27 of 27)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [A Recipe for Watermarking Diffusion Models](https://mlsanity.com/paper/2303.10137/) (2023)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [Responsible Disclosure of Generative Models Using Scalable Fingerprinting](https://mlsanity.com/paper/2012.08726/) (2020)
- [Origin Tracing and Detecting of LLMs](https://mlsanity.com/paper/2304.14072/) (2023)
- [Few-Shot Detection of Machine-Generated Text using Style Representations](https://mlsanity.com/paper/2401.06712/) (2024)
- [RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification](https://mlsanity.com/paper/1904.08104/) (2019)
- [Progressive Open Space Expansion for Open-Set Model Attribution](https://mlsanity.com/paper/2303.06877/) (2023)
- [GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis](https://mlsanity.com/paper/2407.10471/) (2024)
- [Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling](https://mlsanity.com/paper/2402.09199/) (2024)
- [Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms](https://mlsanity.com/paper/2309.06780/) (2023)
- [WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification](https://mlsanity.com/paper/2409.12121/) (2024)
- [ADD 2023: Towards Audio Deepfake Detection and Analysis in the Wild](https://mlsanity.com/paper/2408.04967/) (2024)
- [Synthetic Speech Classification: IEEE Signal Processing Cup 2022 challenge](https://mlsanity.com/paper/2412.13279/) (2024)

## Built on by (most cited first, 1 of 1)

- [AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS](https://mlsanity.com/paper/2608.22186/) (2026)

## Abstract (arXiv)

Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This underscores the need for traceable TTS models-systems capable of tracing their synthesized speech without compromising quality or security. However, existing methods predominantly rely on explicit watermarking on speech or on vocoder, which degrades speech quality and is vulnerable to spoofing. To address these limitations, we propose a novel framework for model attribution. Instead of embedding watermarks, we train the TTS model and discriminator using a joint training method that significantly improves traceability generalization while preserving-and even slightly improving-audio quality. This is the first work toward watermark-free TTS with strong traceability. To promote progress in related fields, we will release the code upon acceptance of the paper.