@inproceedings{acosta-triana-etal-2024-annotheia-semi,
title = "{A}nno{T}heia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies",
author = "Acosta-Triana, Jos{\'e}-M. and
Gimeno-G{\'o}mez, David and
Mart{\'\i}nez-Hinarejos, Carlos-D.",
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.113",
pages = "1260--1269",
abstract = "More than 7,000 known languages are spoken around the world. However, due to the lack of annotated resources, only a small fraction of them are currently covered by speech technologies. Albeit self-supervised speech representations, recent massive speech corpora collections, as well as the organization of challenges, have alleviated this inequality, most studies are mainly benchmarked on English. This situation is aggravated when tasks involving both acoustic and visual speech modalities are addressed. In order to promote research on low-resource languages for audio-visual speech technologies, we present AnnoTheia, a semi-automatic annotation toolkit that detects when a person speaks on the scene and the corresponding transcription. In addition, to show the complete process of preparing AnnoTheia for a language of interest, we also describe the adaptation of a pre-trained model for active speaker detection to Spanish, using a database not initially conceived for this type of task. Prior evaluations show that the toolkit is able to speed up to four times the annotation process. The AnnoTheia toolkit, tutorials, and pre-trained models are available at https://github.com/joactr/AnnoTheia/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="acosta-triana-etal-2024-annotheia-semi">
<titleInfo>
<title>AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">José-M.</namePart>
<namePart type="family">Acosta-Triana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Gimeno-Gómez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos-D.</namePart>
<namePart type="family">Martínez-Hinarejos</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>More than 7,000 known languages are spoken around the world. However, due to the lack of annotated resources, only a small fraction of them are currently covered by speech technologies. Albeit self-supervised speech representations, recent massive speech corpora collections, as well as the organization of challenges, have alleviated this inequality, most studies are mainly benchmarked on English. This situation is aggravated when tasks involving both acoustic and visual speech modalities are addressed. In order to promote research on low-resource languages for audio-visual speech technologies, we present AnnoTheia, a semi-automatic annotation toolkit that detects when a person speaks on the scene and the corresponding transcription. In addition, to show the complete process of preparing AnnoTheia for a language of interest, we also describe the adaptation of a pre-trained model for active speaker detection to Spanish, using a database not initially conceived for this type of task. Prior evaluations show that the toolkit is able to speed up to four times the annotation process. The AnnoTheia toolkit, tutorials, and pre-trained models are available at https://github.com/joactr/AnnoTheia/.</abstract>
<identifier type="citekey">acosta-triana-etal-2024-annotheia-semi</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.113</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1260</start>
<end>1269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies
%A Acosta-Triana, José-M.
%A Gimeno-Gómez, David
%A Martínez-Hinarejos, Carlos-D.
%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 acosta-triana-etal-2024-annotheia-semi
%X More than 7,000 known languages are spoken around the world. However, due to the lack of annotated resources, only a small fraction of them are currently covered by speech technologies. Albeit self-supervised speech representations, recent massive speech corpora collections, as well as the organization of challenges, have alleviated this inequality, most studies are mainly benchmarked on English. This situation is aggravated when tasks involving both acoustic and visual speech modalities are addressed. In order to promote research on low-resource languages for audio-visual speech technologies, we present AnnoTheia, a semi-automatic annotation toolkit that detects when a person speaks on the scene and the corresponding transcription. In addition, to show the complete process of preparing AnnoTheia for a language of interest, we also describe the adaptation of a pre-trained model for active speaker detection to Spanish, using a database not initially conceived for this type of task. Prior evaluations show that the toolkit is able to speed up to four times the annotation process. The AnnoTheia toolkit, tutorials, and pre-trained models are available at https://github.com/joactr/AnnoTheia/.
%U https://aclanthology.org/2024.lrec-main.113
%P 1260-1269
Markdown (Informal)
[AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies](https://aclanthology.org/2024.lrec-main.113) (Acosta-Triana et al., LREC-COLING 2024)
ACL