Tracing Decoder Artifacts for Compact Synthetic Speech Screening
cs.SD, cs.AI, eess.AS
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/resemble-ai/chatterbox
Terminology
Sources
- A Fourier Explanation of AI-music Artifacts
- ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
- Towards generalizing deep-audio fake detection networks
- Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints
- OpenVoice: Versatile Instant Voice Cloning
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
- High Fidelity Neural Audio Compression
- Qwen3-TTS Technical Report
- VibeVoice Technical Report
- End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
- Improved DeepFake Detection Using Whisper Features
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
- 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
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment