SOLIDO: A Robust Watermarking Method For Speech Synthesis Via Low-rank Adaptation

Abstract

The accelerated advancement of speech generative models has given rise to security issues, including model infringement and unauthorized abuse of content. Although existing generative watermarking techniques have proposed corresponding solutions, most methods require substantial computational overhead and training costs. In addition, some methods have limitations in robustness when handling variable-length inputs. To tackle these challenges, we propose \textsc\{SOLIDO\}, a novel generative watermarking method that integrates parameter-efficient fine-tuning with speech watermarking through low-rank adaptation (LoRA) for speech diffusion models. Concretely, the watermark encoder converts the watermark to align with the input of diffusion models. To achieve precise watermark extraction from variable-length inputs, the watermark decoder based on depthwise separable convolution is designed for watermark recovery. To further enhance speech generation performance and watermark extraction capa

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2025solido

Related papers

• Collaborative Watermarking For Adversarial Speech Synthesis (2023)0.00
• GROOT: Generating Robust Watermark For Diffusion-model-based Audio Synthesis (2024)6.77
• Audio Codec Augmentation For Robust Collaborative Watermarking Of Speech Synthesis (2024)4.52
• P2mark: Plug-and-play Parameter-level Watermarking For Neural Speech Generation (2025)0.00
• Trinimark: A Robust Generative Speech Watermarking Method For Trinity-level Traceability (2025)0.00
• AWARE: Audio Watermarking With Adversarial Resistance To Edits (2025)0.00
• A Domain Adaptation Framework For Speech Recognition Systems With Only Synthetic Data (2025)5.24
• DLPO: Diffusion Model Loss-guided Reinforcement Learning For Fine-tuning Text-to-speech Diffusion Models (2024)0.00