MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
Paper • 2510.10396 • Published
Yu Zhang
AaronZ345
AI & ML interests
Multi-Modal Generative AI (Spatial Audio/Music/Singing/Speech).
Recent Activity
new activity 4 days ago
GTSinger/GTSinger:Annotation quality is very low, not usable for training authored a paper 6 months ago
MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with
Refined Annotations authored a paper 7 months ago
ASAudio: A Survey of Advanced Spatial Audio ResearchOrganizations
Annotation quality is very low, not usable for training
1
#8 opened 4 days ago
by 
da1sypetals-iota
authored a
paper 6 months ago
authored a
paper 7 months ago
upvoted a paper 7 months ago
updated a
dataset 8 months ago
updated a
dataset 9 months ago
authored a
paper 9 months ago
liked a
dataset 9 months ago
authored 3
papers 9 months ago
Leveraging Pretrained Diffusion Models for Zero-Shot Part Assembly
Paper • 2505.00426 • Published
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
Paper • 2505.14910 • Published • 1
STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation
Paper • 2507.06670 • Published
published a
dataset 9 months ago
liked a
dataset 11 months ago
published a
dataset 11 months ago
updated a
model 11 months ago
upvoted 2
papers 11 months ago
authored 3
papers 11 months ago
TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching
Paper • 2502.12572 • Published • 2
MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
Paper • 2502.18924 • Published • 16
Versatile Framework for Song Generation with Prompt-based Control
Paper • 2504.19062 • Published • 6