Yu Zhang's picture

Yu Zhang

AaronZ345

·

https://aaronz345.github.io

AI & ML interests

Multi-Modal Generative AI (Spatial Audio/Music/Singing/Speech).

Recent Activity

new activity 22 days ago

GTSinger/GTSinger:Annotation quality is very low, not usable for training

new activity about 2 months ago

GTSinger/GTSinger:Annotation quality is very low, not usable for training

authored a paper 7 months ago

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

View all activity

Organizations

New activity in GTSinger/GTSinger 22 days ago

Annotation quality is very low, not usable for training

#8 opened about 2 months ago by

da1sypetals-iota

commented 2 papers about 1 year ago

ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting

Paper • 2504.20630 • Published Apr 29, 2025 • 9 •

Versatile Framework for Song Generation with Prompt-based Control

Paper • 2504.19062 • Published Apr 27, 2025 • 6 •

New activity in GTSinger/GTSinger over 1 year ago

What phoneme system do the english an japanese datasets use?

#7 opened over 1 year ago by

Upload 3 files

#6 opened over 1 year ago by

Upload 3 files

#5 opened over 1 year ago by