A supervised audio tokenizer trained with audio tagging labels nearly matches continuous BEATs features for automated audio captioning on Clotho, while conventional discrete tokens degrade performance.
We construct BART-based and GPT-2 XL-based AAC systems, both utilizing semantic and acoustic tokens
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Discrete Audio Representations for Automated Audio Captioning
A supervised audio tokenizer trained with audio tagging labels nearly matches continuous BEATs features for automated audio captioning on Clotho, while conventional discrete tokens degrade performance.