Four text-to-audio systems were evaluated against a human reference in the DCASE 2024 Task 7 challenge, with a 36% quality gap and strong but small-sample FAD-to-human correlation.
Objective Evaluation We employed the Fr ´echet Audio Distance (FAD) [6] with PANN- Wavegram-Logmel [7] embeddings as our primary objective metric
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sound Scene Synthesis at the DCASE 2024 Challenge
Four text-to-audio systems were evaluated against a human reference in the DCASE 2024 Task 7 challenge, with a 36% quality gap and strong but small-sample FAD-to-human correlation.