论文解读
A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR
生成模型 | 7.5/10
生成模型
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
论文解读
Amplifying Membership Signal Through Chained Regeneration
生成模型 | 6.6/10
论文解读
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation
知识蒸馏 | 10/10
论文解读
VeRe-Flow: Guiding Flow Matching toward Clean Speech via Velocity Contrastive Regularization and Representation Alignment for Noise-Robust Bandwidth Expansion
语音增强 | 7.7/10
论文解读
Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
语音合成 | 7.5/10
论文解读
Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement
语音增强 | 6.6/10
论文解读
Time-Unconditional Generative Speech Enhancement via Autonomous Rectified Flow
语音增强 | 7.0/10
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
PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement
语音增强 | 7.6/10
论文解读
AUDEDIT: Inversion-Free Text-Guided Editing with Pretrained Audio Flow Models
生成模型 | 7.8/10
论文解读
DuraMark: Duration-Embedded Watermarking in LLM-based TTS
生成模型 | 8.7/10
论文解读
FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
音频生成 | 9/10
论文解读
Towards Robust Generative Speech Enhancement Using Vector Quantisation-Based Neural Audio Codec
语音增强 | 5.9/10
论文解读
MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion
语音转换 | 6.9/10
论文解读
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
语音分离 | 8.4/10
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
SB-RF: Schrödinger Bridge Rectified Flow for One-Step Robust Speech Enhancement
语音增强 | 7.6/10
论文解读
Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching
空间音频 | 7.9/10
论文解读
SURF: Separation via Unsupervised Remixing Flow
无监督学习 | 6.4/10
论文解读
A Comparison of Generative and Discriminative Methods for Speech Enhancement: Robustness, Complexity, and Hallucination
语音增强 | 8.3/10