@inproceedings{huang-etal-2026-hw,
title = "{HW}-{TSC}{'}s Submissions to the {IWSLT} 2026 Offline Speech Translation Task",
author = "Huang, Boqi 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
He, Yu and
Lan, Xiaoqing",
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-1.9/",
pages = "84--90",
ISBN = "979-8-89176-411-8",
abstract = "This paper describes the HW-TSC{'}s submission to the IWSLT 2026 Offline Speech Translation Task, specifically for the English-to-Chinese and English-to-German unconstrained tracks. Our system adopts a robust cascade architecture optimized for long-form, unsegmented audio. To mitigate the hallucination and inconsistency issues common in long-sequence processing, we propose a two-pass transcription strategy: an initial streaming ASR with a 12-second context buffer for sentence-level coherence, followed by Qwen3-ForcedAligner for precise timestamping. Based on these alignments, a second-pass refinement is conducted using Qwen3-Omni on re-segmented 30-second chunks to ensure high-fidelity transcriptions. For the translation module, we employ a context-aware segment merging strategy (up to 150 tokens) to empower the Qwen3 llm with sufficient semantic context. Experimental results on the tst-2022 benchmark demonstrate the effectiveness of our pipeline, achieving COMET scores of 0.8462 (En-Zh) and 0.7854 (En-De), significantly outperforming the standard cascade baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-hw">
<titleInfo>
<title>HW-TSC’s Submissions to the IWSLT 2026 Offline Speech Translation Task</title>
</titleInfo>
<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">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">Yu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Lan</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 describes the HW-TSC’s submission to the IWSLT 2026 Offline Speech Translation Task, specifically for the English-to-Chinese and English-to-German unconstrained tracks. Our system adopts a robust cascade architecture optimized for long-form, unsegmented audio. To mitigate the hallucination and inconsistency issues common in long-sequence processing, we propose a two-pass transcription strategy: an initial streaming ASR with a 12-second context buffer for sentence-level coherence, followed by Qwen3-ForcedAligner for precise timestamping. Based on these alignments, a second-pass refinement is conducted using Qwen3-Omni on re-segmented 30-second chunks to ensure high-fidelity transcriptions. For the translation module, we employ a context-aware segment merging strategy (up to 150 tokens) to empower the Qwen3 llm with sufficient semantic context. Experimental results on the tst-2022 benchmark demonstrate the effectiveness of our pipeline, achieving COMET scores of 0.8462 (En-Zh) and 0.7854 (En-De), significantly outperforming the standard cascade baselines.</abstract>
<identifier type="citekey">huang-etal-2026-hw</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.9/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>84</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Submissions to the IWSLT 2026 Offline Speech Translation Task
%A Huang, Boqi
%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 He, Yu
%A Lan, Xiaoqing
%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 huang-etal-2026-hw
%X This paper describes the HW-TSC’s submission to the IWSLT 2026 Offline Speech Translation Task, specifically for the English-to-Chinese and English-to-German unconstrained tracks. Our system adopts a robust cascade architecture optimized for long-form, unsegmented audio. To mitigate the hallucination and inconsistency issues common in long-sequence processing, we propose a two-pass transcription strategy: an initial streaming ASR with a 12-second context buffer for sentence-level coherence, followed by Qwen3-ForcedAligner for precise timestamping. Based on these alignments, a second-pass refinement is conducted using Qwen3-Omni on re-segmented 30-second chunks to ensure high-fidelity transcriptions. For the translation module, we employ a context-aware segment merging strategy (up to 150 tokens) to empower the Qwen3 llm with sufficient semantic context. Experimental results on the tst-2022 benchmark demonstrate the effectiveness of our pipeline, achieving COMET scores of 0.8462 (En-Zh) and 0.7854 (En-De), significantly outperforming the standard cascade baselines.
%U https://aclanthology.org/2026.iwslt-1.9/
%P 84-90
Markdown (Informal)
[HW-TSC’s Submissions to the IWSLT 2026 Offline Speech Translation Task](https://aclanthology.org/2026.iwslt-1.9/) (Huang et al., IWSLT 2026)
ACL
- Boqi Huang, Daimeng Wei, Jiaxin GUO, Yuanchang Luo, Hengchao Shang, Zongyao Li, Zhiqiang Rao, Jinlong Yang, Zhanglin Wu, Yu He, and Xiaoqing Lan. 2026. HW-TSC’s Submissions to the IWSLT 2026 Offline Speech Translation Task. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 84–90, San Diego, USA (in-person and online). Association for Computational Linguistics.