ELSA introduces an event-level semantic alignment metric for reference-free text-to-audio evaluation that reports higher correlation with human ratings than CLAP-based baselines across four benchmarks.
A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation
ELSA introduces an event-level semantic alignment metric for reference-free text-to-audio evaluation that reports higher correlation with human ratings than CLAP-based baselines across four benchmarks.