论文解读
克隆与匿名本是一体两面：把 27k 小时的 TTS 直接当成隐私滤镜
语音转换 | 8.0/10
语音转换
论文解读
Speaker-Normalized Semantic Speech Tokens via Iterative S2U-T2U Refinement
语音编码 | 6.0/10
论文解读
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
语音合成 | 6.5/10
论文解读
AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks
语音伪造检测 | 8.4/10
论文解读
Cloned Voices, Real Consequences: Evaluating Bias in Political Deepfake Detection for Electoral Integrity in Brazil
语音伪造检测 | 7.7/10
论文解读
Designed Vocalizations Dataset: Sound-Designed Human and Animal Voices for Non-human Voice Conversion
语音转换 | 7.9/10
论文解读
Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture
语音转换 | 6.9/10
论文解读
Adapting a Diffusion-Based Music Synthesis Model to Human Voice Conversion
语音转换 | 6.0/10
论文解读
Goodbye Equal Error Rate, Hello Local Information Disclosure: Evaluating Voice Anonymisation against 1-to-N Linkage Threats
语音转换 | 6.5/10
论文解读
NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization
语音转换 | 5.9/10
论文解读
OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL
语音识别 | 7.5/10
论文解读
ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion
语音转换 | 6.6/10
论文解读
RIVET: Robust Idempotent Voice Attribute Editing
语音转换 | 8/10
论文解读
Zero-VC: Zero-Lookahead Streaming Voice Conversion via Speaker Anonymization
语音转换 | 6.1/10
论文解读
DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization
语音转换 | 6.5/10
论文解读
SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space
语音转换 | 6.8/10
论文解读
TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion
语音转换 | 6.8/10
论文解读
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
语音合成 | 8.9/10
论文解读
UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion
语音合成 | 8.2/10
论文解读
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
语音合成 | 10/10