@inproceedings{sevilla-etal-2024-automated-extraction,
title = "Automated Extraction of Prosodic Structure from Unannotated Sign Language Video",
author = "Sevilla, Antonio F. G. and
Lahoz-Bengoechea, Jos{\'e} Mar{\'\i}a and
Diaz, Alberto",
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.161",
pages = "1808--1816",
abstract = "As in oral phonology, prosody is an important carrier of linguistic information in sign languages. One of the most prominent ways this reveals itself is in the time structure of signs: their rhythm and intensity of articulation. To be able to empirically see these effects, the velocity of the hands can be computed throughout the execution of a sign. In this article, we propose a method for extracting this information from unlabeled videos of sign language, exploiting CoTracker, a recent advancement in computer vision which can track every point in a video without the need of any calibration or fine-tuning. The dominant hand is identified via clustering of the computed point velocities, and its dynamic profile plotted to make apparent the prosodic structure of signing. We apply our method to different datasets and sign languages, and perform a preliminary visual exploration of results. This exploration supports the usefulness of our methodology for linguistic analysis, though issues to be tackled remain, such as bi-manual signs and a formal and numerical evaluation of accuracy. Nonetheless, the absence of any preprocessing requirements may make it useful for other researchers and datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sevilla-etal-2024-automated-extraction">
<titleInfo>
<title>Automated Extraction of Prosodic Structure from Unannotated Sign Language Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">F</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Sevilla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">María</namePart>
<namePart type="family">Lahoz-Bengoechea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Diaz</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>As in oral phonology, prosody is an important carrier of linguistic information in sign languages. One of the most prominent ways this reveals itself is in the time structure of signs: their rhythm and intensity of articulation. To be able to empirically see these effects, the velocity of the hands can be computed throughout the execution of a sign. In this article, we propose a method for extracting this information from unlabeled videos of sign language, exploiting CoTracker, a recent advancement in computer vision which can track every point in a video without the need of any calibration or fine-tuning. The dominant hand is identified via clustering of the computed point velocities, and its dynamic profile plotted to make apparent the prosodic structure of signing. We apply our method to different datasets and sign languages, and perform a preliminary visual exploration of results. This exploration supports the usefulness of our methodology for linguistic analysis, though issues to be tackled remain, such as bi-manual signs and a formal and numerical evaluation of accuracy. Nonetheless, the absence of any preprocessing requirements may make it useful for other researchers and datasets.</abstract>
<identifier type="citekey">sevilla-etal-2024-automated-extraction</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.161</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1808</start>
<end>1816</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Extraction of Prosodic Structure from Unannotated Sign Language Video
%A Sevilla, Antonio F. G.
%A Lahoz-Bengoechea, José María
%A Diaz, Alberto
%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 sevilla-etal-2024-automated-extraction
%X As in oral phonology, prosody is an important carrier of linguistic information in sign languages. One of the most prominent ways this reveals itself is in the time structure of signs: their rhythm and intensity of articulation. To be able to empirically see these effects, the velocity of the hands can be computed throughout the execution of a sign. In this article, we propose a method for extracting this information from unlabeled videos of sign language, exploiting CoTracker, a recent advancement in computer vision which can track every point in a video without the need of any calibration or fine-tuning. The dominant hand is identified via clustering of the computed point velocities, and its dynamic profile plotted to make apparent the prosodic structure of signing. We apply our method to different datasets and sign languages, and perform a preliminary visual exploration of results. This exploration supports the usefulness of our methodology for linguistic analysis, though issues to be tackled remain, such as bi-manual signs and a formal and numerical evaluation of accuracy. Nonetheless, the absence of any preprocessing requirements may make it useful for other researchers and datasets.
%U https://aclanthology.org/2024.lrec-main.161
%P 1808-1816
Markdown (Informal)
[Automated Extraction of Prosodic Structure from Unannotated Sign Language Video](https://aclanthology.org/2024.lrec-main.161) (Sevilla et al., LREC-COLING 2024)
ACL