wenxiang guo's picture

wenxiang guo

verstar

·

AI & ML interests

None yet

Recent Activity

published a dataset about 6 hours ago

upvoted a paper 14 days ago

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

upvoted a paper 14 days ago

Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

View all activity

Organizations

Papers 1

arxiv:2504.20630

models 2

verstar/STARS

Updated Jul 16, 2025 • 1

verstar/TechSinger

Text-to-Speech • Updated Apr 23, 2025 • 2

datasets 4

verstar/SO-FOA

Updated about 6 hours ago

verstar/MRSAudio

Viewer • Updated Oct 22, 2025 • 131k • 60.4k • 7

verstar/MRSTest_en

Updated Sep 28, 2025 • 24

verstar/MRSTest

Updated Sep 28, 2025 • 31