@inproceedings{maina-etal-2026-perceptual,
title = "Perceptual Validation of 3{D} Pose, Guided Sign Language Synthesis",
author = "Maina, Ezekiel and
Wanzare, Lilian and
Obuhuma, James",
editor = "Efthimiou, Eleni and
Fotinea, Stavroula-Evita and
Hanke, Thomas and
Hochgesang, Julie A. and
Mesch, Johanna and
Schulder, Marc",
booktitle = "Proceedings of the {LREC} 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.signlang-1.33/",
doi = "10.63317/29qyih7xu7ym",
pages = "315--323",
abstract = "Sign language corpora face a structural tension between open-access requirements and the irreducible biometric identity embedded in visual, gestural data. While 3D pose estimation enables signer-agnostic abstraction, the representational adequacy of pose-based modeling for preserving linguistic structure remains underexplored. This paper introduces a perceptually-grounded kinematic modeling framework that formalizes 3D landmark sequences as an intermediate linguistic representation and validates their adequacy through avatar-mediated synthesis and large-scale human evaluation. Using 30370 gloss-level Kenyan Sign Language (KSL) segments derived from the AI4KSL corpus, we construct normalized 3D motion trajectories via MediaPipe Holistic. These trajectories are retargeted to parameterized avatars through a constrained kinematic mapping that preserves non-manual marker geometry and articulatory timing. We define a dual evaluation paradigm combining geometric fidelity metrics (PCK=92.7{\%}, OKS=0.88, PCP=91.5{\%}, PDJ{\ensuremath{>}}85.3{\%}) with perceptual constructs measured across a statistically powered Deaf participant cohort (N=384). Results demonstrate a strong predictive relationship between structural joint precision and perceived gesture clarity (r=0.76, p{\ensuremath{<}}.01), suggesting that linguistic adequacy is partially recoverable from normalized kinematic structure. Furthermore, representational diversity in avatar instantiation significantly increases perceived inclusivity without degrading intelligibility. These findings establish pose-based motion abstraction not merely as an anonymization technique but as a viable corpus-level modeling layer for ethically sustainable language in motion."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maina-etal-2026-perceptual">
<titleInfo>
<title>Perceptual Validation of 3D Pose, Guided Sign Language Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ezekiel</namePart>
<namePart type="family">Maina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilian</namePart>
<namePart type="family">Wanzare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Obuhuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleni</namePart>
<namePart type="family">Efthimiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stavroula-Evita</namePart>
<namePart type="family">Fotinea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Hanke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Hochgesang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Mesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Schulder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sign language corpora face a structural tension between open-access requirements and the irreducible biometric identity embedded in visual, gestural data. While 3D pose estimation enables signer-agnostic abstraction, the representational adequacy of pose-based modeling for preserving linguistic structure remains underexplored. This paper introduces a perceptually-grounded kinematic modeling framework that formalizes 3D landmark sequences as an intermediate linguistic representation and validates their adequacy through avatar-mediated synthesis and large-scale human evaluation. Using 30370 gloss-level Kenyan Sign Language (KSL) segments derived from the AI4KSL corpus, we construct normalized 3D motion trajectories via MediaPipe Holistic. These trajectories are retargeted to parameterized avatars through a constrained kinematic mapping that preserves non-manual marker geometry and articulatory timing. We define a dual evaluation paradigm combining geometric fidelity metrics (PCK=92.7%, OKS=0.88, PCP=91.5%, PDJ\ensuremath>85.3%) with perceptual constructs measured across a statistically powered Deaf participant cohort (N=384). Results demonstrate a strong predictive relationship between structural joint precision and perceived gesture clarity (r=0.76, p\ensuremath<.01), suggesting that linguistic adequacy is partially recoverable from normalized kinematic structure. Furthermore, representational diversity in avatar instantiation significantly increases perceived inclusivity without degrading intelligibility. These findings establish pose-based motion abstraction not merely as an anonymization technique but as a viable corpus-level modeling layer for ethically sustainable language in motion.</abstract>
<identifier type="citekey">maina-etal-2026-perceptual</identifier>
<identifier type="doi">10.63317/29qyih7xu7ym</identifier>
<location>
<url>https://aclanthology.org/2026.signlang-1.33/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>315</start>
<end>323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perceptual Validation of 3D Pose, Guided Sign Language Synthesis
%A Maina, Ezekiel
%A Wanzare, Lilian
%A Obuhuma, James
%Y Efthimiou, Eleni
%Y Fotinea, Stavroula-Evita
%Y Hanke, Thomas
%Y Hochgesang, Julie A.
%Y Mesch, Johanna
%Y Schulder, Marc
%S Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F maina-etal-2026-perceptual
%X Sign language corpora face a structural tension between open-access requirements and the irreducible biometric identity embedded in visual, gestural data. While 3D pose estimation enables signer-agnostic abstraction, the representational adequacy of pose-based modeling for preserving linguistic structure remains underexplored. This paper introduces a perceptually-grounded kinematic modeling framework that formalizes 3D landmark sequences as an intermediate linguistic representation and validates their adequacy through avatar-mediated synthesis and large-scale human evaluation. Using 30370 gloss-level Kenyan Sign Language (KSL) segments derived from the AI4KSL corpus, we construct normalized 3D motion trajectories via MediaPipe Holistic. These trajectories are retargeted to parameterized avatars through a constrained kinematic mapping that preserves non-manual marker geometry and articulatory timing. We define a dual evaluation paradigm combining geometric fidelity metrics (PCK=92.7%, OKS=0.88, PCP=91.5%, PDJ\ensuremath>85.3%) with perceptual constructs measured across a statistically powered Deaf participant cohort (N=384). Results demonstrate a strong predictive relationship between structural joint precision and perceived gesture clarity (r=0.76, p\ensuremath<.01), suggesting that linguistic adequacy is partially recoverable from normalized kinematic structure. Furthermore, representational diversity in avatar instantiation significantly increases perceived inclusivity without degrading intelligibility. These findings establish pose-based motion abstraction not merely as an anonymization technique but as a viable corpus-level modeling layer for ethically sustainable language in motion.
%R 10.63317/29qyih7xu7ym
%U https://aclanthology.org/2026.signlang-1.33/
%U https://doi.org/10.63317/29qyih7xu7ym
%P 315-323
Markdown (Informal)
[Perceptual Validation of 3D Pose, Guided Sign Language Synthesis](https://aclanthology.org/2026.signlang-1.33/) (Maina et al., SignLang 2026)
ACL
- Ezekiel Maina, Lilian Wanzare, and James Obuhuma. 2026. Perceptual Validation of 3D Pose, Guided Sign Language Synthesis. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 315–323, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).