@inproceedings{klezovich-etal-2026-comparison,
title = "Comparison of Low Bitrate Quantizers for Encoding {S}wedish {S}ign {L}anguage",
author = "Klezovich, Anna and
Mesch, Johanna and
Henter, Gustav Eje and
Beskow, Jonas",
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-1.27/",
doi = "10.63317/54ffsuydifyk",
pages = "256--261",
abstract = "This paper investigates the bitrate{--}distortion trade-off of different discrete representations for Swedish Sign Language (STS) using the STS Mocap v1 motion capture dataset. We compare the K-Means algorithm with the Residual Vector Quantized Variational Autoencoder (RQ-VAE) to determine how efficiently each method preserves salient motion information at low bitrates. The results show that RQ-VAE consistently achieves lower reconstruction error than K-Means at matching bitrates, particularly for body motion, and better preserves the signing space volume. We further demonstrate that quantized representations can serve as conditioning for a flow-matching generative model, producing plausible but still imperfect sign sequences at low bitrates. These findings highlight the advantages of vector quantized models for efficient sign language motion encoding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klezovich-etal-2026-comparison">
<titleInfo>
<title>Comparison of Low Bitrate Quantizers for Encoding Swedish Sign Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Klezovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Mesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustav</namePart>
<namePart type="given">Eje</namePart>
<namePart type="family">Henter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Beskow</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>This paper investigates the bitrate–distortion trade-off of different discrete representations for Swedish Sign Language (STS) using the STS Mocap v1 motion capture dataset. We compare the K-Means algorithm with the Residual Vector Quantized Variational Autoencoder (RQ-VAE) to determine how efficiently each method preserves salient motion information at low bitrates. The results show that RQ-VAE consistently achieves lower reconstruction error than K-Means at matching bitrates, particularly for body motion, and better preserves the signing space volume. We further demonstrate that quantized representations can serve as conditioning for a flow-matching generative model, producing plausible but still imperfect sign sequences at low bitrates. These findings highlight the advantages of vector quantized models for efficient sign language motion encoding.</abstract>
<identifier type="citekey">klezovich-etal-2026-comparison</identifier>
<identifier type="doi">10.63317/54ffsuydifyk</identifier>
<location>
<url>https://aclanthology.org/2026.signlang-1.27/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>256</start>
<end>261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparison of Low Bitrate Quantizers for Encoding Swedish Sign Language
%A Klezovich, Anna
%A Mesch, Johanna
%A Henter, Gustav Eje
%A Beskow, Jonas
%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 klezovich-etal-2026-comparison
%X This paper investigates the bitrate–distortion trade-off of different discrete representations for Swedish Sign Language (STS) using the STS Mocap v1 motion capture dataset. We compare the K-Means algorithm with the Residual Vector Quantized Variational Autoencoder (RQ-VAE) to determine how efficiently each method preserves salient motion information at low bitrates. The results show that RQ-VAE consistently achieves lower reconstruction error than K-Means at matching bitrates, particularly for body motion, and better preserves the signing space volume. We further demonstrate that quantized representations can serve as conditioning for a flow-matching generative model, producing plausible but still imperfect sign sequences at low bitrates. These findings highlight the advantages of vector quantized models for efficient sign language motion encoding.
%R 10.63317/54ffsuydifyk
%U https://aclanthology.org/2026.signlang-1.27/
%U https://doi.org/10.63317/54ffsuydifyk
%P 256-261
Markdown (Informal)
[Comparison of Low Bitrate Quantizers for Encoding Swedish Sign Language](https://aclanthology.org/2026.signlang-1.27/) (Klezovich et al., SignLang 2026)
ACL