Pith. sign in

Leveraging pre-trained bert for audio captioning,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.SD 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Discrete Audio Representations for Automated Audio Captioning

cs.SD · 2025-05-21 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Discrete Audio Representations for Automated Audio Captioning cs.SD · 2025-05-21 · conditional · none · ref 8

    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.