每日研究速递
语音/音乐/音频论文速递 2026-06-19
共分析 40 篇语音/AI 论文
扩散模型
论文解读
Audio-to-Audio via Diffusion Warm Initialization
音频生成 | 7.6/10
论文解读
One-Step Token-to-Waveform Generation with MeanFlow in Latent Space
语音合成 | 9.3/10
论文解读
AdaTT: Text-Guided Instrument Timbre Transfer with Target-Adaptive Structural Control
音频生成 | 8.7/10
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
Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentation
语音活动检测 | 5.9/10
论文解读
Joycent: Diffusion-based Accent TTS without Accented Phone Prediction
语音合成 | 6.8/10
论文解读
MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
语音生成 | 6.9/10
论文解读
Unified Audio Generation and Editing via Joint Condition Modeling and Progressive Training
音频生成 | 8.7/10
论文解读
FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision
语音合成 | 7/10
论文解读
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
语音合成 | 6.8/10
论文解读
PianoKontext: Expressive Performance Rendering from Deadpan Context
音乐生成 | 9.1/10
论文解读
Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models
语音分离 | 7.3/10
论文解读
Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
语音合成 | 7.3/10
论文解读
Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation
语音识别 | 8.3/10
论文解读
HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis
语音合成 | 9/10
论文解读
Your U-Net Dereverberation Model is Secretly an RIR Encoder
对比学习 | 8.3/10
论文解读
DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
扩散模型 | 7.5/10
论文解读
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
音乐生成 | 4.2/10
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