@inproceedings{harada-etal-2024-impressions,
title = "Can Impressions of Music be Extracted from Thumbnail Images?",
author = "Harada, Takashi and
Motomitsu, Takehiro and
Hayashi, Katsuhiko and
Sakai, Yusuke and
Kamigaito, Hidetaka",
editor = "Kruspe, Anna and
Oramas, Sergio and
Epure, Elena V. and
Sordo, Mohamed and
Weck, Benno and
Doh, SeungHeon and
Won, Minz and
Manco, Ilaria and
Meseguer-Brocal, Gabriel",
booktitle = "Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)",
month = nov,
year = "2024",
address = "Oakland, USA",
publisher = "Association for Computational Lingustics",
url = "https://aclanthology.org/2024.nlp4musa-1.9/",
pages = "49--56",
abstract = "In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs. However, there is a scarcity of large-scale publicly available datasets, consisting of music data and their corresponding natural language descriptions known as music captions. In particular, non-musical information such as suitable situations for listening to a track and the emotions elicited upon listening is crucial for describing music. This type of information is underrepresented in existing music caption datasets due to the challenges associated with extracting it directly from music data. To address this issue, we propose a method for generating music caption data that incorporates non-musical aspects inferred from music thumbnail images, and validated the effectiveness of our approach through human evaluations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="harada-etal-2024-impressions">
<titleInfo>
<title>Can Impressions of Music be Extracted from Thumbnail Images?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Harada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehiro</namePart>
<namePart type="family">Motomitsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhiko</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kruspe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Oramas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Epure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Sordo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Weck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SeungHeon</namePart>
<namePart type="family">Doh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minz</namePart>
<namePart type="family">Won</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilaria</namePart>
<namePart type="family">Manco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Meseguer-Brocal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Lingustics</publisher>
<place>
<placeTerm type="text">Oakland, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs. However, there is a scarcity of large-scale publicly available datasets, consisting of music data and their corresponding natural language descriptions known as music captions. In particular, non-musical information such as suitable situations for listening to a track and the emotions elicited upon listening is crucial for describing music. This type of information is underrepresented in existing music caption datasets due to the challenges associated with extracting it directly from music data. To address this issue, we propose a method for generating music caption data that incorporates non-musical aspects inferred from music thumbnail images, and validated the effectiveness of our approach through human evaluations.</abstract>
<identifier type="citekey">harada-etal-2024-impressions</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4musa-1.9/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>49</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Impressions of Music be Extracted from Thumbnail Images?
%A Harada, Takashi
%A Motomitsu, Takehiro
%A Hayashi, Katsuhiko
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%Y Kruspe, Anna
%Y Oramas, Sergio
%Y Epure, Elena V.
%Y Sordo, Mohamed
%Y Weck, Benno
%Y Doh, SeungHeon
%Y Won, Minz
%Y Manco, Ilaria
%Y Meseguer-Brocal, Gabriel
%S Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)
%D 2024
%8 November
%I Association for Computational Lingustics
%C Oakland, USA
%F harada-etal-2024-impressions
%X In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs. However, there is a scarcity of large-scale publicly available datasets, consisting of music data and their corresponding natural language descriptions known as music captions. In particular, non-musical information such as suitable situations for listening to a track and the emotions elicited upon listening is crucial for describing music. This type of information is underrepresented in existing music caption datasets due to the challenges associated with extracting it directly from music data. To address this issue, we propose a method for generating music caption data that incorporates non-musical aspects inferred from music thumbnail images, and validated the effectiveness of our approach through human evaluations.
%U https://aclanthology.org/2024.nlp4musa-1.9/
%P 49-56
Markdown (Informal)
[Can Impressions of Music be Extracted from Thumbnail Images?](https://aclanthology.org/2024.nlp4musa-1.9/) (Harada et al., NLP4MusA 2024)
ACL
- Takashi Harada, Takehiro Motomitsu, Katsuhiko Hayashi, Yusuke Sakai, and Hidetaka Kamigaito. 2024. Can Impressions of Music be Extracted from Thumbnail Images?. In Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA), pages 49–56, Oakland, USA. Association for Computational Lingustics.