@inproceedings{wang-etal-2024-x,
title = "{X}-{ACE}: Explainable and Multi-factor Audio Captioning Evaluation",
author = "Wang, Qian and
Gu, Jia-Chen and
Ling, Zhen-Hua",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.729",
doi = "10.18653/v1/2024.findings-acl.729",
pages = "12273--12287",
abstract = "Automated audio captioning (AAC) aims to generate descriptions based on audio input, attracting exploration of emerging audio language models (ALMs). However, current evaluation metrics only provide a single score to assess the overall quality of captions without characterizing the nuanced difference by systematically going through an evaluation checklist. To this end, we propose the explainable and multi-factor audio captioning evaluation (X-ACE) paradigm. X-ACE identifies four main factors that constitute the majority of audio features, specifically sound event, source, attribute and relation. To assess a given caption from an ALM, it is firstly transformed into an audio graph, where each node denotes an entity in the caption and corresponds to a factor. On the one hand, graph matching is conducted from part to whole for a holistic assessment. On the other hand, the nodes contained within each factor are aggregated to measure the factor-level performance. The pros and cons of an ALM can be explicitly and clearly demonstrated through X-ACE, pointing out the direction for further improvements. Experiments show that X-ACE exhibits better correlation with human perception and can detect mismatches sensitively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-x">
<titleInfo>
<title>X-ACE: Explainable and Multi-factor Audio Captioning Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia-Chen</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen-Hua</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated audio captioning (AAC) aims to generate descriptions based on audio input, attracting exploration of emerging audio language models (ALMs). However, current evaluation metrics only provide a single score to assess the overall quality of captions without characterizing the nuanced difference by systematically going through an evaluation checklist. To this end, we propose the explainable and multi-factor audio captioning evaluation (X-ACE) paradigm. X-ACE identifies four main factors that constitute the majority of audio features, specifically sound event, source, attribute and relation. To assess a given caption from an ALM, it is firstly transformed into an audio graph, where each node denotes an entity in the caption and corresponds to a factor. On the one hand, graph matching is conducted from part to whole for a holistic assessment. On the other hand, the nodes contained within each factor are aggregated to measure the factor-level performance. The pros and cons of an ALM can be explicitly and clearly demonstrated through X-ACE, pointing out the direction for further improvements. Experiments show that X-ACE exhibits better correlation with human perception and can detect mismatches sensitively.</abstract>
<identifier type="citekey">wang-etal-2024-x</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.729</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.729</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12273</start>
<end>12287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T X-ACE: Explainable and Multi-factor Audio Captioning Evaluation
%A Wang, Qian
%A Gu, Jia-Chen
%A Ling, Zhen-Hua
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-x
%X Automated audio captioning (AAC) aims to generate descriptions based on audio input, attracting exploration of emerging audio language models (ALMs). However, current evaluation metrics only provide a single score to assess the overall quality of captions without characterizing the nuanced difference by systematically going through an evaluation checklist. To this end, we propose the explainable and multi-factor audio captioning evaluation (X-ACE) paradigm. X-ACE identifies four main factors that constitute the majority of audio features, specifically sound event, source, attribute and relation. To assess a given caption from an ALM, it is firstly transformed into an audio graph, where each node denotes an entity in the caption and corresponds to a factor. On the one hand, graph matching is conducted from part to whole for a holistic assessment. On the other hand, the nodes contained within each factor are aggregated to measure the factor-level performance. The pros and cons of an ALM can be explicitly and clearly demonstrated through X-ACE, pointing out the direction for further improvements. Experiments show that X-ACE exhibits better correlation with human perception and can detect mismatches sensitively.
%R 10.18653/v1/2024.findings-acl.729
%U https://aclanthology.org/2024.findings-acl.729
%U https://doi.org/10.18653/v1/2024.findings-acl.729
%P 12273-12287
Markdown (Informal)
[X-ACE: Explainable and Multi-factor Audio Captioning Evaluation](https://aclanthology.org/2024.findings-acl.729) (Wang et al., Findings 2024)
ACL