论文解读
S-PRESSO: Ultra Low Bitrate Sound Effect Compression with Diffusion Autoencoders and Offline Quantization
音频生成 | 7.5/10
音频生成
论文解读
Sounds that Shape: Audio-Driven 3D Mesh Generation with Attribute-Decoupled Score Distillation Sampling
音频生成 | 7.0/10
论文解读
Spring Reverb Emulation with Hybrid Gated Convolutional Networks and State Space Models
音频生成 | 7.5/10
论文解读
StereoFoley: Object-Aware Stereo Audio Generation from Video
音频生成 | 7.5/10
论文解读
StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks
歌唱语音合成 | 7.5/10
论文解读
Subsequence SDTW: Differentiable Alignment with Flexible Boundary Conditions
音乐信息检索 | 8.0/10
论文解读
Sunac: Source-Aware Unified Neural Audio Codec
音频生成 | 7.5/10
论文解读
SwitchCodec: Adaptive Residual-Expert Sparse Quantization for High-Fidelity Neural Audio Coding
音频生成 | 8.5/10
论文解读
Synthcloner: Synthesizer-Style Audio Transfer via Factorized Codec with ADSR Envelope Control
音频生成 | 8.5/10
论文解读
TAG: Structured Temporal Audio Generation via LLM-Guided Manual Scription and Control
音频生成 | 7.5/10
论文解读
Taming Audio VAEs via Target-KL Regularization
音频生成 | 6.5/10
论文解读
Text2Move: Text-To-Moving Sound Generation via Trajectory Prediction and Temporal Alignment
空间音频 | 8.0/10
论文解读
Training-Free Multimodal Guidance for Video to Audio Generation
音频生成 | 8.0/10
论文解读
Universr: Unified and Versatile Audio Super-Resolution Via Vocoder-Free Flow Matching
音频超分辨率 | 8.0/10
论文解读
Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation
音乐生成 | 7.5/10
论文解读
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
音频生成 | 8.5/10
论文解读
Materialistic RIR: Material Conditioned Realistic RIR Generation
音频生成 | 7.5/10
论文解读
BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps
本文针对符号音乐生成中主流的事件序列（event-based）tokenization方法隐含处理时间规律、导致模型需额外学习时间网格的问题，提出了一种名为**BEAT**的新型网格化tokenization框架。其核心思想是将音乐在时间上均匀离散化为“拍”（beat）作为基本单位，将每拍内每个音高
论文解读
Latent Fourier Transform
这篇论文旨在解决现有音乐生成模型难以对**任意时间尺度**上的音乐模式进行精确控制的问题。作者提出了**潜在傅里叶变换（LatentFT）** 框架，其核心是将离散傅里叶变换应用于由扩散自编码器编码得到的**潜在向量序列**，从而得到“潜在频谱”。通过在训练过程中对潜在频谱进行随机频率掩码，迫使解码
论文解读
ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
本文提出了ControlFoley，一个统一且可控的视频到音频生成框架，旨在解决现有方法在跨模态冲突下文本控制力弱、以及参考音频控制中音色与时间信息纠缠的问题。其核心贡献包括：1）提出联合视觉编码范式