@inproceedings{lan-etal-2026-hw,
title = "{HW}-{TSC}{'}s Submission to the {IWSLT} 2026 Subtitling Track",
author = "Lan, Xiaoqing and
Wei, Daimeng and
GUO, Jiaxin and
Luo, Yuanchang and
Shang, Hengchao and
Li, Zongyao and
Rao, Zhiqiang and
Yang, Jinlong and
Wu, Zhanglin and
Huang, Boqi and
He, Yu",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.10/",
pages = "91--96",
ISBN = "979-8-89176-411-8",
abstract = "This paper introduces HW-TSC{'}s submission to the IWSLT 2026 Subtitling track. For automatic subtitle generation, we employ a cascaded strategy under unconstrained conditions. First, we construct a large-model-based streaming speech recognition framework, which incorporates VAD voice activity detection, sliding-window context caching, long audio chunking, and the Qwen3 forced alignment model to achieve high-precision transcription and timestamping from English speech to text. Next, we perform text translation using a Qwen3-based translation model. Finally, according to subtitle constraints such as characters per second (CPS) and characters per line (CPL), we identify translation segments that exceed compliance thresholds via quantitative evaluation, and rewrite them using a large language model while preserving core semantic meaning, ultimately producing subtitle files that meet the required standards."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lan-etal-2026-hw">
<titleInfo>
<title>HW-TSC’s Submission to the IWSLT 2026 Subtitling Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">GUO</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanchang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">He</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 23rd International Conference on Spoken Language Translation (IWSLT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<abstract>This paper introduces HW-TSC’s submission to the IWSLT 2026 Subtitling track. For automatic subtitle generation, we employ a cascaded strategy under unconstrained conditions. First, we construct a large-model-based streaming speech recognition framework, which incorporates VAD voice activity detection, sliding-window context caching, long audio chunking, and the Qwen3 forced alignment model to achieve high-precision transcription and timestamping from English speech to text. Next, we perform text translation using a Qwen3-based translation model. Finally, according to subtitle constraints such as characters per second (CPS) and characters per line (CPL), we identify translation segments that exceed compliance thresholds via quantitative evaluation, and rewrite them using a large language model while preserving core semantic meaning, ultimately producing subtitle files that meet the required standards.</abstract>
<identifier type="citekey">lan-etal-2026-hw</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.10/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>91</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Submission to the IWSLT 2026 Subtitling Track
%A Lan, Xiaoqing
%A Wei, Daimeng
%A GUO, Jiaxin
%A Luo, Yuanchang
%A Shang, Hengchao
%A Li, Zongyao
%A Rao, Zhiqiang
%A Yang, Jinlong
%A Wu, Zhanglin
%A Huang, Boqi
%A He, Yu
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F lan-etal-2026-hw
%X This paper introduces HW-TSC’s submission to the IWSLT 2026 Subtitling track. For automatic subtitle generation, we employ a cascaded strategy under unconstrained conditions. First, we construct a large-model-based streaming speech recognition framework, which incorporates VAD voice activity detection, sliding-window context caching, long audio chunking, and the Qwen3 forced alignment model to achieve high-precision transcription and timestamping from English speech to text. Next, we perform text translation using a Qwen3-based translation model. Finally, according to subtitle constraints such as characters per second (CPS) and characters per line (CPL), we identify translation segments that exceed compliance thresholds via quantitative evaluation, and rewrite them using a large language model while preserving core semantic meaning, ultimately producing subtitle files that meet the required standards.
%U https://aclanthology.org/2026.iwslt-1.10/
%P 91-96
Markdown (Informal)
[HW-TSC’s Submission to the IWSLT 2026 Subtitling Track](https://aclanthology.org/2026.iwslt-1.10/) (Lan et al., IWSLT 2026)
ACL
- Xiaoqing Lan, Daimeng Wei, Jiaxin GUO, Yuanchang Luo, Hengchao Shang, Zongyao Li, Zhiqiang Rao, Jinlong Yang, Zhanglin Wu, Boqi Huang, and Yu He. 2026. HW-TSC’s Submission to the IWSLT 2026 Subtitling Track. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 91–96, San Diego, USA (in-person and online). Association for Computational Linguistics.