# VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection

arXiv: https://arxiv.org/abs/2601.22556 · HTML: https://mlsanity.com/paper/2601.22556/

## Key facts

- Cited by 1 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 31 of its 52 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## 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, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [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)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec](https://mlsanity.com/paper/2305.02765/) (2023)
- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior](https://mlsanity.com/paper/2106.06406/) (2021)
- [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)
- [AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA](https://mlsanity.com/paper/2405.11135/) (2024)
- [Detecting Voice Cloning Attacks via Timbre Watermarking](https://mlsanity.com/paper/2312.03410/) (2023)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [WMAdapter: Adding WaterMark Control to Latent Diffusion Models](https://mlsanity.com/paper/2406.08337/) (2024)
- [Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models](https://mlsanity.com/paper/2412.05167/) (2024)
- [LaWa: Using Latent Space for In-Generation Image Watermarking](https://mlsanity.com/paper/2408.05868/) (2024)
- [Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2412.06602/) (2024)
- [DeAR: A Deep-learning-based Audio Re-recording Resilient Watermarking](https://mlsanity.com/paper/2212.02339/) (2022)
- [Fewer-token Neural Speech Codec with Time-invariant Codes](https://mlsanity.com/paper/2310.00014/) (2023)
- [Latent Watermarking of Audio Generative Models](https://mlsanity.com/paper/2409.02915/) (2024)
- [TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking](https://mlsanity.com/paper/2406.04840/) (2024)

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

- [MusicMark: A Robust Generative Watermarking Framework for Music Generation](https://mlsanity.com/paper/2607.11117/) (2026)

## Abstract (arXiv)

Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they rely either on simple superposition in the noise space or on intrusive alterations to model weights. To bridge this gap, we propose VocBulwark, an additional-parameter injection framework that freezes generative model parameters to preserve perceptual quality. Specifically, we design a Temporal Adapter to deeply entangle watermarks with acoustic attributes, synergizing with a Coarse-to-Fine Gated Extractor to resist advanced attacks. Furthermore, we develop an Accuracy-Guided Optimization Curriculum that dynamically orchestrates gradient flow to resolve the optimization conflict between fidelity and robustness. Comprehensive experiments demonstrate that VocBulwark achieves high-capacity and high-fidelity watermarking, offering robust defense against complex practical scenarios, with resilience to Codec regenerations and variable-length manipulations.