Towards Trustworthy Mobile Speech Interaction: Ensuring Voice Authenticity and Transmission Integrity
cs.SD, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- WavMark: Watermarking for Audio Generation
- Kimi-Audio Technical Report
- Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- Zero-shot Voice Conversion with Diffusion Transformers
- AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
- AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- Proactive Detection of Voice Cloning with Localized Watermarking
- Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
- WaveNet: A Generative Model for Raw Audio
- CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking
- OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion
- SpeechVerifier: Robust Acoustic Fingerprint against Tampering Attacks via Watermarking
- Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- 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