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

Michael Finkelson

1 indexed paper

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

Publications per year

1
26

Top categories

Sound×1AI×1Vision×1

Frequent co-authors

Daniel Segal1×
Eitan Richardson1×
Shahar Armon1×
Nani Goldring1×
Poriya Panet1×
Nir Zabari1×

Research Timeline

2026
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

The paper presents ScenA, a method for generating rich conversational audio using a text-to-audio flow-matching foundation model conditioned on multiple reference voices and a free-form natural language prompt.

Highlighted terms show continued research focus across papers

Papers

cs.SDcs.AIcs.CVEmpiricalRecentJun 17, 2026

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

Michael Finkelson, Daniel Segal, Eitan Richardson, Shahar Armon +6 more

The paper presents ScenA, a method for generating rich conversational audio using a text-to-audio flow-matching foundation model conditioned on multiple reference voices and a free-form natural langua…

View →