# Attributable-Watermarking of Speech Generative Models

arXiv: https://arxiv.org/abs/2202.08900 · HTML: https://mlsanity.com/paper/2202.08900/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 12 of 12)

- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [Image Generators with Conditionally-Independent Pixel Synthesis](https://mlsanity.com/paper/2011.13775/) (2020)
- [High Fidelity Speech Synthesis with Adversarial Networks](https://mlsanity.com/paper/1909.11646/) (2019)
- [Source Generator Attribution via Inversion](https://mlsanity.com/paper/1905.02259/) (2019)
- [Voice Impersonation using Generative Adversarial Networks](https://mlsanity.com/paper/1802.06840/) (2018)
- [Decentralized Attribution of Generative Models](https://mlsanity.com/paper/2010.13974/) (2020)
- [On Attribution of Deepfakes](https://mlsanity.com/paper/2008.09194/) (2020)

## Built on by (most cited first, 5 of 5)

- [SoK: Watermarking for AI-Generated Content](https://mlsanity.com/paper/2411.18479/) (2024)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation](https://mlsanity.com/paper/2504.15035/) (2025)
- [TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Traceability](https://mlsanity.com/paper/2504.20532/) (2025)

## Abstract (arXiv)

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a solution for model attribution, i.e., the classification of synthetic contents by their source models via watermarks embedded in the contents. Building on past success of model attribution in the image domain, we discuss algorithmic improvements for generating user-end speech models that empirically achieve high attribution accuracy, while maintaining high generation quality. We show the trade off between attributability and generation quality under a variety of attacks on generated speech signals attempting to remove the watermarks, and the feasibility of learning robust watermarks against these attacks.