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

Serban Mihalache

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Audio and Speech Processing×2

Frequent co-authors

Cristian-Teodor Neamtu2×
Stefan Smeu2×
Dan Oneata2×
Horia Cucu2×
Dragos Burileanu2×

Research Timeline

2026
Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning

The paper proposes a metric learning framework for TTS source attribution and out-of-distribution detection.

Towards Zero-Shot Attribution of Synthetic Speech via Audio-Text Contrastive Retrieval

This paper proposes a new approach to audio deepfake attribution that can identify the system that generated an audio clip without retraining or updating the classifier.

Highlighted terms show continued research focus across papers

Papers

eess.ASEmpiricalRecentSep 18, 2026

Towards Zero-Shot Attribution of Synthetic Speech via Audio-Text Contrastive Retrieval

Cristian-Teodor Neamtu, Serban Mihalache, Stefan Smeu, Dan Oneata +2 more

This paper proposes a new approach to audio deepfake attribution that can identify the system that generated an audio clip without retraining or updating the classifier.

View →
eess.ASEmpiricalRecent
Jun 9, 2026

Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning

Cristian-Teodor Neamtu, Serban Mihalache, Stefan Smeu, Dan Oneata +2 more

The paper proposes a metric learning framework for TTS source attribution and out-of-distribution detection.

View →