论文解读
Improving Automatic Speech Recognition by Mitigating Distortions Introduced by Speech Enhancement Under Drone Noise
语音识别 | 6.5/10
扩散模型
论文解读
InstructAudio: Unified Speech and Music Generation with Natural Language Instruction
语音合成 | 7.5/10
论文解读
Instrument Generation Through Distributional Flow Matching and Test-Time Search
音乐生成 | 7.0/10
论文解读
KSDIFF: Keyframe-Augmented Speech-Aware Dual-Path Diffusion for Facial Animation
音频生成 | 7.5/10
论文解读
LAFUFU: Latent Acoustic Features For Ultra-Fast Utterance Restoration
语音增强 | 8.0/10
论文解读
Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
音频生成 | 7.5/10
论文解读
Leveraging Diffusion U-Net Features for Predominant Instrument Recognition
音乐信息检索 | 8.0/10
论文解读
Low-Resource Guidance for Controllable Latent Audio Diffusion
音乐生成 | 8.5/10
论文解读
MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation Without Vector Quantization
音频生成 | 8.0/10
论文解读
MELA-TTS: Joint Transformer-Diffusion Model with Representation Alignment for Speech Synthesis
语音合成 | 7.0/10
论文解读
Membership Inference Attack against Music Diffusion Models via Generative Manifold Perturbation
音频安全 | 7.5/10
论文解读
MirrorTalk: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
语音合成 | 7.0/10
论文解读
Mitigating Data Replication in Text-to-Audio Generative Diffusion Models Through Anti-Memorization Guidance
音频生成 | 7.5/10
论文解读
用带噪混合当高噪声步监督：Mix2Morph 如何把加法叠加训练成可控的声音注入
📄 用带噪混合当高噪声步监督：Mix2Morph 如何把加法叠加训练成可控的声音注入 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460386
论文解读
Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation
音频生成 | 7.5/10
论文解读
Noise-to-Notes: Diffusion-Based Generation and Refinement for Automatic Drum Transcription
音乐信息检索 | 8.0/10
论文解读
PG-SE: Predictive Acceleration and Correction for Generative Speech Enhancement
语音增强 | 7.5/10
论文解读
PICOAUDIO2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
音频生成 | 7.5/10
论文解读
PRoADS: Provably Secure And Robust Audio Diffusion Steganography With Latent Optimization And Backward Euler Inversion
音频安全 | 6.5/10
论文解读
PromptSep: Generative Audio Separation Via Multimodal Prompting
语音分离 | 7.5/10