@inproceedings{r-etal-2025-continuous,
title = "Continuous Fingerspelling Dataset for {I}ndian {S}ign {L}anguage",
author = "R, Kirandevraj and
Kurmi, Vinod K. and
Namboodiri, Vinay P. and
Jawahar, C.v.",
editor = "Hasanuzzaman, Mohammed and
Quiroga, Facundo Manuel and
Modi, Ashutosh and
Kamila, Sabyasachi and
Artiaga, Keren and
Joshi, Abhinav and
Singh, Sanjeet",
booktitle = "Proceedings of the Workshop on Sign Language Processing (WSLP)",
month = dec,
year = "2025",
address = "IIT Bombay, Mumbai, India (Co-located with IJCNLP{--}AACL 2025)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wslp-main.6/",
pages = "33--38",
ISBN = "979-8-89176-304-3",
abstract = "Fingerspelling enables signers to represent proper nouns and technical terms letter-by-letter using manual alphabets, yet remains severely under-resourced for Indian Sign Language (ISL). We present the first continuous fingerspelling dataset for ISL, extracted from the ISH News YouTube channel, in which fingerspelling is accompanied by synchronized on-screen text cues. The dataset comprises 1,308 segments from 499 videos, totaling 70.85 minutes and 14,814 characters, with aligned video-text pairs capturing authentic coarticulation patterns. We validated the dataset quality through annotation using a proficient ISL interpreter, achieving a 90.67{\%} exact match rate for 150 samples. We further established baseline recognition benchmarks using a ByT5-small encoder-decoder model, which attains 82.91{\%} Character Error Rate after fine-tuning. This resource supports multiple downstream tasks, including fingerspelling transcription, temporal localization, and sign generation. The dataset is available at the following link: https://kirandevraj.github.io/ISL-Fingerspelling/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="r-etal-2025-continuous">
<titleInfo>
<title>Continuous Fingerspelling Dataset for Indian Sign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kirandevraj</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinod</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Kurmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinay</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Namboodiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C.v.</namePart>
<namePart type="family">Jawahar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Sign Language Processing (WSLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Quiroga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keren</namePart>
<namePart type="family">Artiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">IIT Bombay, Mumbai, India (Co-located with IJCNLP–AACL 2025)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-304-3</identifier>
</relatedItem>
<abstract>Fingerspelling enables signers to represent proper nouns and technical terms letter-by-letter using manual alphabets, yet remains severely under-resourced for Indian Sign Language (ISL). We present the first continuous fingerspelling dataset for ISL, extracted from the ISH News YouTube channel, in which fingerspelling is accompanied by synchronized on-screen text cues. The dataset comprises 1,308 segments from 499 videos, totaling 70.85 minutes and 14,814 characters, with aligned video-text pairs capturing authentic coarticulation patterns. We validated the dataset quality through annotation using a proficient ISL interpreter, achieving a 90.67% exact match rate for 150 samples. We further established baseline recognition benchmarks using a ByT5-small encoder-decoder model, which attains 82.91% Character Error Rate after fine-tuning. This resource supports multiple downstream tasks, including fingerspelling transcription, temporal localization, and sign generation. The dataset is available at the following link: https://kirandevraj.github.io/ISL-Fingerspelling/.</abstract>
<identifier type="citekey">r-etal-2025-continuous</identifier>
<location>
<url>https://aclanthology.org/2025.wslp-main.6/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>33</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Continuous Fingerspelling Dataset for Indian Sign Language
%A R, Kirandevraj
%A Kurmi, Vinod K.
%A Namboodiri, Vinay P.
%A Jawahar, C.v.
%Y Hasanuzzaman, Mohammed
%Y Quiroga, Facundo Manuel
%Y Modi, Ashutosh
%Y Kamila, Sabyasachi
%Y Artiaga, Keren
%Y Joshi, Abhinav
%Y Singh, Sanjeet
%S Proceedings of the Workshop on Sign Language Processing (WSLP)
%D 2025
%8 December
%I Association for Computational Linguistics
%C IIT Bombay, Mumbai, India (Co-located with IJCNLP–AACL 2025)
%@ 979-8-89176-304-3
%F r-etal-2025-continuous
%X Fingerspelling enables signers to represent proper nouns and technical terms letter-by-letter using manual alphabets, yet remains severely under-resourced for Indian Sign Language (ISL). We present the first continuous fingerspelling dataset for ISL, extracted from the ISH News YouTube channel, in which fingerspelling is accompanied by synchronized on-screen text cues. The dataset comprises 1,308 segments from 499 videos, totaling 70.85 minutes and 14,814 characters, with aligned video-text pairs capturing authentic coarticulation patterns. We validated the dataset quality through annotation using a proficient ISL interpreter, achieving a 90.67% exact match rate for 150 samples. We further established baseline recognition benchmarks using a ByT5-small encoder-decoder model, which attains 82.91% Character Error Rate after fine-tuning. This resource supports multiple downstream tasks, including fingerspelling transcription, temporal localization, and sign generation. The dataset is available at the following link: https://kirandevraj.github.io/ISL-Fingerspelling/.
%U https://aclanthology.org/2025.wslp-main.6/
%P 33-38
Markdown (Informal)
[Continuous Fingerspelling Dataset for Indian Sign Language](https://aclanthology.org/2025.wslp-main.6/) (R et al., WSLP 2025)
ACL
- Kirandevraj R, Vinod K. Kurmi, Vinay P. Namboodiri, and C.v. Jawahar. 2025. Continuous Fingerspelling Dataset for Indian Sign Language. In Proceedings of the Workshop on Sign Language Processing (WSLP), pages 33–38, IIT Bombay, Mumbai, India (Co-located with IJCNLP–AACL 2025). Association for Computational Linguistics.