VoXtream2: Full-stream TTS with dynamic speaking rate control
Paper • 2603.13518 • Published • 1
Nikita Torgashov PRO
herimor
AI & ML interests
Text-to-Speech, Speaker Recognition
Recent Activity
liked a dataset about 16 hours ago
facebook/omnilingual-asr-corpus liked a model 1 day ago
fishaudio/s2-pro new activity 2 days ago
herimor/voxtream2:Add authors, library_name and link to paper pageOrganizations
authored a
paper 2 days ago
submitted a
paper to Daily Papers 3 days ago
authored 4
papers 6 months ago
VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency
Paper • 2509.15969 • Published • 3
Reshape Dimensions Network for Speaker Recognition
Paper • 2407.18223 • Published
The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description
Paper • 2308.08294 • Published
LRPD: Large Replay Parallel Dataset
Paper • 2309.17298 • Published