论文解读
FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation
音频生成 | 8.6/10
音频生成
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。
- 视频到声音生成 直接 59 篇 · 含子树 59 篇
论文解读
WaveNet-Style Guitar Amplifier Model Pruning for Real-Time iOS Deployment
音频生成 | 8.0/10
论文解读
Structural Bottlenecks on Frequency Representation in End-to-End Audio Models
音频生成 | 7.6/10
论文解读
Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space
音视频生成 | 7.4/10
论文解读
Unified Audio Intelligence Without Regressing on Text Intelligence
音频交互 | 6.8/10
论文解读
AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
语音合成 | 7.6/10
论文解读
AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
音频生成 | 5.8/10
论文解读
Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio Attacks
语音识别 | 7.6/10
论文解读
STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
音频生成 | 7.9/10
论文解读
Two-dimensional quantization for geometry-aware audio coding
语音编码 | 7.6/10
论文解读
Predicting Timbre Traits for Interpretable Assessment of Musical Sound Synthesizers
音频生成 | 6.1/10
论文解读
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
语音合成 | 7.9/10
论文解读
LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
音频水印 | 8/10
论文解读
STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
音频生成 | 8.8/10
论文解读
Audio-to-Audio via Diffusion Warm Initialization
音频生成 | 7.6/10
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
FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
音频生成 | 9/10
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
AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation
音频生成 | 9/10