论文解读
Token-Based Audio Inpainting via Discrete Diffusion
音频生成 | 7.5/10
扩散模型
论文解读
VibeVoice: Expressive Podcast Generation with Next-Token Diffusion
语音合成 | 8.5/10
论文解读
ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
条件生成 | 8.0/10
论文解读
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
音频生成 | 8.5/10
论文解读
DiffAnon: Diffusion-based Prosody Control for Voice Anonymization
语音匿名化 | 7.5/10
论文解读
Diffusion Reconstruction towards Generalizable Audio Deepfake Detection
音频深度伪造检测 | 7.5/10
论文解读
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
音视频 | 8.5/10
论文解读
A State-Dependent Markov Diffusion Process for Generative Speech Enhancement
语音增强 | 6.5/10
论文解读
Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
语音增强 | 7.5/10
论文解读
Asynchrony-Aware Decoupled Multimodal Control for Cued Speech Video Generation
语音合成 | 7.5/10
论文解读
Audience-Aware Co-speech Gesture Generation in Public Speaking via Anticipation Tokens
音频生成 | 8.0/10
论文解读
Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
语音识别 | 7.0/10
论文解读
AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation
音频生成 | 7.5/10
论文解读
Automatic Music Mixing Using a Generative Model of Effect Embeddings
音乐生成 | 7.5/10
论文解读
Bayesian Signal Separation Via Plug-and-Play Diffusion-Within-Gibbs Sampling
语音分离 | 7.5/10
论文解读
Beyond Face Swapping: A Diffusion-Based Digital Human Benchmark for Multimodal Deepfake Detection
音频深度伪造检测 | 8.1/10
论文解读
Bone-Conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models
语音增强 | 7.5/10
论文解读
Break-the-Beat! Controllable MIDI-to-Drum audio synthesis
音乐生成 | 7.5/10
论文解读
Bridging the Measurement–Simulation Gap in Room Acoustics with Real2sim Diffusion
声源定位 | 8.5/10
论文解读
Cardiobridge-DM: Bridging Cross-Cohort Heart Sound Synthesis via Rhythm-Aware Semi-Supervised Diffusion
音频生成 | 7.5/10