Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wijngaard, Gijs, Formisano, Elia, Giordano, Bruno L., Dumontier, Michel
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.18572
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910386609979392
author Wijngaard, Gijs
Formisano, Elia
Giordano, Bruno L.
Dumontier, Michel
author_facet Wijngaard, Gijs
Formisano, Elia
Giordano, Bruno L.
Dumontier, Michel
contents Automated Audio Captioning is a multimodal task that aims to convert audio content into natural language. The assessment of audio captioning systems is typically based on quantitative metrics applied to text data. Previous studies have employed metrics derived from machine translation and image captioning to evaluate the quality of generated audio captions. Drawing inspiration from auditory cognitive neuroscience research, we introduce a novel metric approach -- Audio Captioning Evaluation on Semantics of Sound (ACES). ACES takes into account how human listeners parse semantic information from sounds, providing a novel and comprehensive evaluation perspective for automated audio captioning systems. ACES combines semantic similarities and semantic entity labeling. ACES outperforms similar automated audio captioning metrics on the Clotho-Eval FENSE benchmark in two evaluation categories.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18572
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds
Wijngaard, Gijs
Formisano, Elia
Giordano, Bruno L.
Dumontier, Michel
Sound
Audio and Speech Processing
Automated Audio Captioning is a multimodal task that aims to convert audio content into natural language. The assessment of audio captioning systems is typically based on quantitative metrics applied to text data. Previous studies have employed metrics derived from machine translation and image captioning to evaluate the quality of generated audio captions. Drawing inspiration from auditory cognitive neuroscience research, we introduce a novel metric approach -- Audio Captioning Evaluation on Semantics of Sound (ACES). ACES takes into account how human listeners parse semantic information from sounds, providing a novel and comprehensive evaluation perspective for automated audio captioning systems. ACES combines semantic similarities and semantic entity labeling. ACES outperforms similar automated audio captioning metrics on the Clotho-Eval FENSE benchmark in two evaluation categories.
title ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2403.18572