@inproceedings{kermani-etal-2026-temporal,
title = "Temporal-Linguistic Adaptive Streaming for Continuous Sign Language Translation",
author = "Kermani, Arshia and
Irani, Habib and
Ross, Deautaun and
Metsis, Vangelis",
editor = "Yan, Qianqi and
Montariol, Syrielle and
Fan, Yue and
Gu, Jing and
Pan, Jiayi and
Li, Manling and
Kordjamshidi, Parisa and
Suhr, Alane and
Wang, Xin Eric",
booktitle = "Proceedings of the 4th Workshop on Advances in Language and Vision Research ({ALVR})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.alvr-main.21/",
pages = "239--248",
ISBN = "979-8-89176-398-2",
abstract = "Real-time sign language translation must generate text incrementally as signs arrive, yet existing streaming policies treat glosses as a flat token sequence and discard the temporal rhythm of signing. Inter-gloss pauses reliably mark sentence boundaries in continuous discourse, but policies such as Wait-k cause arbitrary cross-boundary fragmentation. We propose Temporal-Linguistic Adaptive Streaming (TLAS), which fuses a Temporal Pause Detector (TPD, tracking inter-gloss interval statistics via an exponential moving average) and a Linguistic Readiness Estimator (LRE, a trained neural head on a frozen T5 encoder) through an Adaptive Fusion Gate (AFG). A proactive timeout fires before the next gloss arrives when the inter-gloss gap exceeds a threshold, producing clean sentence segmentation without oracle boundary information. We also contribute a synthetic discourse dataset of 1,400 ASL discourse groups with LLM-generated per-gloss timestamps and introduce a continuous-stream evaluation paradigm requiring autonomous boundary detection from an unbroken gloss stream. Under such conditions, TLAS significantly outperforms current heuristic baselines, such as Wait-k, and methods relying solely on linguistic content."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kermani-etal-2026-temporal">
<titleInfo>
<title>Temporal-Linguistic Adaptive Streaming for Continuous Sign Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arshia</namePart>
<namePart type="family">Kermani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Habib</namePart>
<namePart type="family">Irani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deautaun</namePart>
<namePart type="family">Ross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vangelis</namePart>
<namePart type="family">Metsis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianqi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alane</namePart>
<namePart type="family">Suhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="given">Eric</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-398-2</identifier>
</relatedItem>
<abstract>Real-time sign language translation must generate text incrementally as signs arrive, yet existing streaming policies treat glosses as a flat token sequence and discard the temporal rhythm of signing. Inter-gloss pauses reliably mark sentence boundaries in continuous discourse, but policies such as Wait-k cause arbitrary cross-boundary fragmentation. We propose Temporal-Linguistic Adaptive Streaming (TLAS), which fuses a Temporal Pause Detector (TPD, tracking inter-gloss interval statistics via an exponential moving average) and a Linguistic Readiness Estimator (LRE, a trained neural head on a frozen T5 encoder) through an Adaptive Fusion Gate (AFG). A proactive timeout fires before the next gloss arrives when the inter-gloss gap exceeds a threshold, producing clean sentence segmentation without oracle boundary information. We also contribute a synthetic discourse dataset of 1,400 ASL discourse groups with LLM-generated per-gloss timestamps and introduce a continuous-stream evaluation paradigm requiring autonomous boundary detection from an unbroken gloss stream. Under such conditions, TLAS significantly outperforms current heuristic baselines, such as Wait-k, and methods relying solely on linguistic content.</abstract>
<identifier type="citekey">kermani-etal-2026-temporal</identifier>
<location>
<url>https://aclanthology.org/2026.alvr-main.21/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>239</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal-Linguistic Adaptive Streaming for Continuous Sign Language Translation
%A Kermani, Arshia
%A Irani, Habib
%A Ross, Deautaun
%A Metsis, Vangelis
%Y Yan, Qianqi
%Y Montariol, Syrielle
%Y Fan, Yue
%Y Gu, Jing
%Y Pan, Jiayi
%Y Li, Manling
%Y Kordjamshidi, Parisa
%Y Suhr, Alane
%Y Wang, Xin Eric
%S Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-398-2
%F kermani-etal-2026-temporal
%X Real-time sign language translation must generate text incrementally as signs arrive, yet existing streaming policies treat glosses as a flat token sequence and discard the temporal rhythm of signing. Inter-gloss pauses reliably mark sentence boundaries in continuous discourse, but policies such as Wait-k cause arbitrary cross-boundary fragmentation. We propose Temporal-Linguistic Adaptive Streaming (TLAS), which fuses a Temporal Pause Detector (TPD, tracking inter-gloss interval statistics via an exponential moving average) and a Linguistic Readiness Estimator (LRE, a trained neural head on a frozen T5 encoder) through an Adaptive Fusion Gate (AFG). A proactive timeout fires before the next gloss arrives when the inter-gloss gap exceeds a threshold, producing clean sentence segmentation without oracle boundary information. We also contribute a synthetic discourse dataset of 1,400 ASL discourse groups with LLM-generated per-gloss timestamps and introduce a continuous-stream evaluation paradigm requiring autonomous boundary detection from an unbroken gloss stream. Under such conditions, TLAS significantly outperforms current heuristic baselines, such as Wait-k, and methods relying solely on linguistic content.
%U https://aclanthology.org/2026.alvr-main.21/
%P 239-248
Markdown (Informal)
[Temporal-Linguistic Adaptive Streaming for Continuous Sign Language Translation](https://aclanthology.org/2026.alvr-main.21/) (Kermani et al., ALVR 2026)
ACL