arxiv:2504.20630
wenxiang guo
verstar
AI & ML interests
None yet
Recent Activity
upvoted a paper 12 minutes ago
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios upvoted a paper 12 minutes ago
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer upvoted a paper about 4 hours ago
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue