@inproceedings{kim-etal-2024-emosical,
title = "Emosical: An Emotion-Annotated Musical Theatre Dataset",
author = "Kim, Hayoon and
Choi, Ahyeon and
Lee, Sungho and
Jung, Hyun Jin and
Lee, Kyogu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.241/",
doi = "10.18653/v1/2024.findings-emnlp.241",
pages = "4169--4180",
abstract = "This paper presents Emosical, a multimodal open-source dataset of musical films. Emosical comprises video, vocal audio, text, and character identity paired samples with annotated emotion tags. Emosical provides rich emotion annotations for each sample by inferring the background story of the characters. To achieve this, we leverage the musical theatre script, which contains the characters' complete background stories and narrative contexts. The annotation pipeline includes feeding the speaking character, text, global persona, and context of the dialogue and song track into a large language model. To verify the effectiveness of our tagging scheme, we perform an ablation study by bypassing each step of the pipeline. The ablation results show the usefulness of each component in generating accurate emotion tags. A subjective test is conducted to compare the generated tags of each ablation result. We also perform a statistical analysis to find out the global characteristics of the collected emotion tags. Emosical would enable expressive synthesis and tagging of the speech and singing voice in the musical theatre domain in future research. Emosical is publicly available at https://github.com/gillosae/emosical."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-emosical">
<titleInfo>
<title>Emosical: An Emotion-Annotated Musical Theatre Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hayoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahyeon</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyun</namePart>
<namePart type="given">Jin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyogu</namePart>
<namePart type="family">Lee</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>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents Emosical, a multimodal open-source dataset of musical films. Emosical comprises video, vocal audio, text, and character identity paired samples with annotated emotion tags. Emosical provides rich emotion annotations for each sample by inferring the background story of the characters. To achieve this, we leverage the musical theatre script, which contains the characters’ complete background stories and narrative contexts. The annotation pipeline includes feeding the speaking character, text, global persona, and context of the dialogue and song track into a large language model. To verify the effectiveness of our tagging scheme, we perform an ablation study by bypassing each step of the pipeline. The ablation results show the usefulness of each component in generating accurate emotion tags. A subjective test is conducted to compare the generated tags of each ablation result. We also perform a statistical analysis to find out the global characteristics of the collected emotion tags. Emosical would enable expressive synthesis and tagging of the speech and singing voice in the musical theatre domain in future research. Emosical is publicly available at https://github.com/gillosae/emosical.</abstract>
<identifier type="citekey">kim-etal-2024-emosical</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.241</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.241/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>4169</start>
<end>4180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Emosical: An Emotion-Annotated Musical Theatre Dataset
%A Kim, Hayoon
%A Choi, Ahyeon
%A Lee, Sungho
%A Jung, Hyun Jin
%A Lee, Kyogu
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kim-etal-2024-emosical
%X This paper presents Emosical, a multimodal open-source dataset of musical films. Emosical comprises video, vocal audio, text, and character identity paired samples with annotated emotion tags. Emosical provides rich emotion annotations for each sample by inferring the background story of the characters. To achieve this, we leverage the musical theatre script, which contains the characters’ complete background stories and narrative contexts. The annotation pipeline includes feeding the speaking character, text, global persona, and context of the dialogue and song track into a large language model. To verify the effectiveness of our tagging scheme, we perform an ablation study by bypassing each step of the pipeline. The ablation results show the usefulness of each component in generating accurate emotion tags. A subjective test is conducted to compare the generated tags of each ablation result. We also perform a statistical analysis to find out the global characteristics of the collected emotion tags. Emosical would enable expressive synthesis and tagging of the speech and singing voice in the musical theatre domain in future research. Emosical is publicly available at https://github.com/gillosae/emosical.
%R 10.18653/v1/2024.findings-emnlp.241
%U https://aclanthology.org/2024.findings-emnlp.241/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.241
%P 4169-4180
Markdown (Informal)
[Emosical: An Emotion-Annotated Musical Theatre Dataset](https://aclanthology.org/2024.findings-emnlp.241/) (Kim et al., Findings 2024)
ACL
- Hayoon Kim, Ahyeon Choi, Sungho Lee, Hyun Jin Jung, and Kyogu Lee. 2024. Emosical: An Emotion-Annotated Musical Theatre Dataset. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4169–4180, Miami, Florida, USA. Association for Computational Linguistics.