GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
cs.SD, cs.AI, cs.CR
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/ZConJugaTe/GAMW
Sources
- WavMark: Watermarking for Audio Generation
- VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
- GLM-TTS Technical Report
- High Fidelity Neural Audio Compression
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
- SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
- Detecting Voice Cloning Attacks via Timbre Watermarking
- XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
- Deep Audio Watermarks are Shallow: Limitations of Post-Hoc Watermarking Techniques for Speech
- A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?
- Copyright Protection in Generative AI: A Technical Perspective
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- Proactive Detection of Voice Cloning with Localized Watermarking
- UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
- SilentCipher: Deep Audio Watermarking
- WaveNet: A Generative Model for Raw Audio
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs