HW-TSC’s Submission to the IWSLT 2026 Subtitling Track

HW-TSC submitted a cascaded system to the IWSLT 2026 Subtitling track, using a large-model-based streaming speech recognition framework with VAD, sliding-window context caching, long audio chunking, and Qwen3 forced alignment for high-precision transcription and timestamping. Text translation was performed with a Qwen3-based model, and subtitle constraints were enforced by rewriting non-compliant segments with a large language model while preserving semantics.

HW-TSC’s Submission to the IWSLT 2026 Subtitling Track https://aclanthology.org/2026.iwslt-1.10.pdf Xiaoqing Lan /people/xiaoqing-lan/unverified/ , Daimeng Wei /people/daimeng-wei/unverified/ , Jiaxin GUO /people/jiaxin-guo/ , Yuanchang Luo /people/yuanchang-luo/unverified/ , Hengchao Shang /people/hengchao-shang/ , Zongyao Li /people/zongyao-li/ , Zhiqiang Rao /people/zhiqiang-rao/unverified/ , Jinlong Yang /people/jinlong-yang/unverified/ , Zhanglin Wu /people/zhanglin-wu/ , Boqi Huang /people/boqi-huang/unverified/ , Yu He /people/yu-he/unverified/ 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.- Anthology ID: - 2026.iwslt-1.10 - Volume: Proceedings of the 23rd International Conference on Spoken Language Translation IWSLT 2026 /volumes/2026.iwslt-1/ - Month: - July - Year: - 2026 - Address: - San Diego, USA in-person and online - Editors: Elizabeth Salesky /people/elizabeth-salesky/ , Antonios Anastasopoulos /people/antonios-anastasopoulos/ , Matteo Negri /people/matteo-negri/ , Marcello Federico /people/marcello-federico/ - Venues: IWSLT /venues/iwslt/ | WS /venues/ws/ - SIG: SIGSLT /sigs/sigslt/ - Publisher: - Association for Computational Linguistics - Note: - Pages: - 91–96 - Language: - URL: https://aclanthology.org/2026.iwslt-1.10/ https://aclanthology.org/2026.iwslt-1.10/ - DOI: - Cite 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 https://aclanthology.org/2026.iwslt-1.10/ . 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. - Cite Informal : HW-TSC’s Submission to the IWSLT 2026 Subtitling Track https://aclanthology.org/2026.iwslt-1.10/ Lan et al., IWSLT 2026 - PDF: https://aclanthology.org/2026.iwslt-1.10.pdf https://aclanthology.org/2026.iwslt-1.10.pdf