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

Kanon Amemiya

1 indexed paper

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

Publications per year

1
26

Top categories

Audio and Speech Processing×1Sound×1

Frequent co-authors

Shuntaro Suzuki1×
Kento Tokura1×
Daichi Yashima1×
Komei Sugiura1×
Shinnosuke Takamichi1×

Research Timeline

2026
ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation

The paper proposes ELSA, a reference-free evaluation metric for fine-grained text-audio alignment in text-to-audio generation.

Highlighted terms show continued research focus across papers

Papers

eess.AScs.SDEmpiricalRecentJun 16, 2026

ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation

Shuntaro Suzuki, Kento Tokura, Daichi Yashima, Kanon Amemiya +2 more

The paper proposes ELSA, a reference-free evaluation metric for fine-grained text-audio alignment in text-to-audio generation.

View →