@inproceedings{kuznetsova-strapparava-2024-multimodal-multilingual,
title = "Multimodal and Multilingual Laughter Detection in Stand-Up Comedy Videos",
author = "Kuznetsova, Anna and
Strapparava, Carlo",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1037",
pages = "11884--11889",
abstract = "This paper presents the development of a novel multimodal multilingual dataset in Russian and English, with a particular emphasis on the exploration of laughter detection techniques. Data was collected from YouTube stand-up comedy videos with manually annotated subtitles, and our research covers data preparation and laughter labeling. We explore two laughter detection approaches presented in the literature: peak detection using preprocessed voiceless audio with an energy-based algorithm and machine learning approach with pretrained models to identify laughter presence and duration. While the machine learning approach currently outperforms peak detection in accuracy and generalization, the latter shows promise and warrants further study. Additionally, we explore unimodal and multimodal humor detection on the new dataset, showing the effectiveness of neural models in capturing humor in both languages, even with textual data. Multimodal experiments indicate that even basic models benefit from visual data, improving detection results. However, further research is needed to enhance laughter detection labeling quality and fully understand the impact of different modalities in a multimodal and multilingual context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuznetsova-strapparava-2024-multimodal-multilingual">
<titleInfo>
<title>Multimodal and Multilingual Laughter Detection in Stand-Up Comedy Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kuznetsova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Strapparava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the development of a novel multimodal multilingual dataset in Russian and English, with a particular emphasis on the exploration of laughter detection techniques. Data was collected from YouTube stand-up comedy videos with manually annotated subtitles, and our research covers data preparation and laughter labeling. We explore two laughter detection approaches presented in the literature: peak detection using preprocessed voiceless audio with an energy-based algorithm and machine learning approach with pretrained models to identify laughter presence and duration. While the machine learning approach currently outperforms peak detection in accuracy and generalization, the latter shows promise and warrants further study. Additionally, we explore unimodal and multimodal humor detection on the new dataset, showing the effectiveness of neural models in capturing humor in both languages, even with textual data. Multimodal experiments indicate that even basic models benefit from visual data, improving detection results. However, further research is needed to enhance laughter detection labeling quality and fully understand the impact of different modalities in a multimodal and multilingual context.</abstract>
<identifier type="citekey">kuznetsova-strapparava-2024-multimodal-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1037</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11884</start>
<end>11889</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal and Multilingual Laughter Detection in Stand-Up Comedy Videos
%A Kuznetsova, Anna
%A Strapparava, Carlo
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kuznetsova-strapparava-2024-multimodal-multilingual
%X This paper presents the development of a novel multimodal multilingual dataset in Russian and English, with a particular emphasis on the exploration of laughter detection techniques. Data was collected from YouTube stand-up comedy videos with manually annotated subtitles, and our research covers data preparation and laughter labeling. We explore two laughter detection approaches presented in the literature: peak detection using preprocessed voiceless audio with an energy-based algorithm and machine learning approach with pretrained models to identify laughter presence and duration. While the machine learning approach currently outperforms peak detection in accuracy and generalization, the latter shows promise and warrants further study. Additionally, we explore unimodal and multimodal humor detection on the new dataset, showing the effectiveness of neural models in capturing humor in both languages, even with textual data. Multimodal experiments indicate that even basic models benefit from visual data, improving detection results. However, further research is needed to enhance laughter detection labeling quality and fully understand the impact of different modalities in a multimodal and multilingual context.
%U https://aclanthology.org/2024.lrec-main.1037
%P 11884-11889
Markdown (Informal)
[Multimodal and Multilingual Laughter Detection in Stand-Up Comedy Videos](https://aclanthology.org/2024.lrec-main.1037) (Kuznetsova & Strapparava, LREC-COLING 2024)
ACL