@inproceedings{wu-etal-2024-futga,
title = "{FUTGA}: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation",
author = "Wu, Junda and
Novack, Zachary and
Namburi, Amit and
Dai, Jiaheng and
Dong, Hao-Wen and
Xie, Zhouhang and
Chen, Carol and
McAuley, Julian",
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-1.17/",
pages = "107--111",
abstract = "We propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the proposed synthetic dataset, FUTGA is enabled to identify the music`s temporal changes at key transition points and their musical functions, as well as generate detailed descriptions for each music segment. We further introduce a full-length music caption dataset generated by FUTGA, as the augmentation of the MusicCaps and the Song Describer datasets. The experiments demonstrate the better quality of the generated captions, which capture the time boundaries of long-form music."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-futga">
<titleInfo>
<title>FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junda</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Novack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Namburi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaheng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao-Wen</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhouhang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carol</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">McAuley</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>We propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the proposed synthetic dataset, FUTGA is enabled to identify the music‘s temporal changes at key transition points and their musical functions, as well as generate detailed descriptions for each music segment. We further introduce a full-length music caption dataset generated by FUTGA, as the augmentation of the MusicCaps and the Song Describer datasets. The experiments demonstrate the better quality of the generated captions, which capture the time boundaries of long-form music.</abstract>
<identifier type="citekey">wu-etal-2024-futga</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4musa-1.17/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>107</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation
%A Wu, Junda
%A Novack, Zachary
%A Namburi, Amit
%A Dai, Jiaheng
%A Dong, Hao-Wen
%A Xie, Zhouhang
%A Chen, Carol
%A McAuley, Julian
%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 wu-etal-2024-futga
%X We propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the proposed synthetic dataset, FUTGA is enabled to identify the music‘s temporal changes at key transition points and their musical functions, as well as generate detailed descriptions for each music segment. We further introduce a full-length music caption dataset generated by FUTGA, as the augmentation of the MusicCaps and the Song Describer datasets. The experiments demonstrate the better quality of the generated captions, which capture the time boundaries of long-form music.
%U https://aclanthology.org/2024.nlp4musa-1.17/
%P 107-111
Markdown (Informal)
[FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation](https://aclanthology.org/2024.nlp4musa-1.17/) (Wu et al., NLP4MusA 2024)
ACL
- Junda Wu, Zachary Novack, Amit Namburi, Jiaheng Dai, Hao-Wen Dong, Zhouhang Xie, Carol Chen, and Julian McAuley. 2024. FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation. In Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA), pages 107–111, Oakland, USA. Association for Computational Lingustics.