论文解读
SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation
音频生成 | 7.6/10
流匹配
论文解读
VIOLET: High-Fidelity Violin Synthesis with Techniques and Dynamics
音乐生成 | 7.6/10
论文解读
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
语音合成 | 7.0/10
论文解读
Rethinking Automatic Music Mixing as Sequential Stem Blending
音乐生成 | 6.5/10
论文解读
InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion
音频质量评估 | 6.4/10
论文解读
OmniVR: Joint Video-Audio Conditional Generation for Restoring Degraded Historical Films
音视频生成 | 7.7/10
论文解读
StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement
语音增强 | 7.0/10
论文解读
CLASVS: Continuous-Latent Autoregression for Melody-Preserving Lyric Editing in Singing Voice Synthesis
自回归模型 | 7.1/10
论文解读
GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
语音合成 | 8.0/10
论文解读
Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling
语音合成 | 6.1/10
论文解读
AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling
语音超分 | 5.9/10
论文解读
P-MUSE: Prompt-MIDI-Optional Model for Unified Instrumental Music Synthesis and Editing
音频理解 | 6.9/10
论文解读
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
音频生成 | 7.1/10
论文解读
RIPPLE: Generating Multi-Channel Phase, Not Recovering It
音频理解 | 7.1/10
论文解读
MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation
音乐生成 | 7.4/10
论文解读
Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm
语音合成 | 7.0/10
论文解读
Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
音乐生成 | 6.8/10
论文解读
FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration
音乐生成 | 7.9/10
论文解读
AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis
语音合成 | 6.9/10
每日研究速递
语音/音乐/音频论文速递 2026-07-20
共分析 15 篇语音/AI 论文