# Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge Distillation

arXiv: https://arxiv.org/abs/2509.19812 · HTML: https://mlsanity.com/paper/2509.19812/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 21 of 21)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking](https://mlsanity.com/paper/2212.02339/) (2022)
- [PROD: Progressive Distillation for Dense Retrieval](https://mlsanity.com/paper/2209.13335/) (2022)
- [SilentCipher: Deep Audio Watermarking](https://mlsanity.com/paper/2406.03822/) (2024)
- [GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis](https://mlsanity.com/paper/2407.10471/) (2024)
- [ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan](https://mlsanity.com/paper/2109.00535/) (2021)
- [Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher](https://mlsanity.com/paper/2110.08532/) (2021)
- [Latent Watermarking of Audio Generative Models](https://mlsanity.com/paper/2409.02915/) (2024)
- [A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?](https://mlsanity.com/paper/2505.19663/) (2025)
- [Follow Your Path: a Progressive Method for Knowledge Distillation](https://mlsanity.com/paper/2107.09305/) (2021)
- [TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking](https://mlsanity.com/paper/2406.04840/) (2024)
- [Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis](https://mlsanity.com/paper/2409.13382/) (2024)
- [A Comparative Study on Proactive and Passive Detection of Deepfake Speech](https://mlsanity.com/paper/2506.14398/) (2025)

## Abstract (arXiv)

With the rapid advancement of speech generative models, unauthorized voice cloning poses significant privacy and security risks. Speech watermarking offers a viable solution for tracing sources and preventing misuse. Current watermarking technologies fall mainly into two categories: DSP-based methods and deep learning-based methods. DSP-based methods are efficient but vulnerable to attacks, whereas deep learning-based methods offer robust protection at the expense of significantly higher computational cost. To improve the computational efficiency and enhance the robustness, we propose PKDMark, a lightweight deep learning-based speech watermarking method that leverages progressive knowledge distillation (PKD). Our approach proceeds in two stages: (1) training a high-performance teacher model using an invertible neural network-based architecture, and (2) transferring the teacher's capabilities to a compact student model through progressive knowledge distillation. This process reduces computational costs by 93.6% while maintaining high level of robust performance and imperceptibility. Experimental results demonstrate that our distilled model achieves an average detection F1 score of 99.6% with a PESQ of 4.30 in advanced distortions, enabling efficient speech watermarking for real-time speech synthesis applications.