Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Sivateja Trikutam

Sivateja Trikutam

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Sound×1NLP×1Audio and Speech Processing×1

Research Timeline

2026
Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer

This paper presents a method for building a compact Hindi text-to-speech model by pruning a large teacher model under a severe data budget, achieving state-of-the-art performance.

Highlighted terms show continued research focus across papers

Papers

cs.SDcs.CLeess.ASEmpiricalRecentJul 19, 2026

Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer

Sivateja Trikutam

This paper presents a method for building a compact Hindi text-to-speech model by pruning a large teacher model under a severe data budget, achieving state-of-the-art performance.

View →