Program

Please follow the links to see the list of papers presented in each session below

DAY 1: July 31 2025

09:00–09:15 Welcome remarks

09:15–10:30 Findings of the IWSLT 2025 Evaluation Campaign (Chair: Jan Niehues)

10:30–11:00 Coffee break

11:00–12:00 Findings of the IWSLT 2025 Evaluation Campaign (Chair: Jan Niehues)

12:00-12:30 Oral Session A (Chair: Marcello Federico)

12:30–14:00 Lunch break

14:00–15:30 Poster Session I: Offline, Instruction Following, Simultaneous, Subtitling, Model Compression

15:30–16:00 Coffee break

16:00–16:30 Oral Session B (Chair: Atul Kr. Ojha)

16:30–17:30 Demo Panel: Advances in the field of speech translation (Chair: Maximilian Awiszus)

17:30 End of day 1

DAY 2: August 1 2025

09:00–10:30 Oral Session C (Chair: Stephan Peitz)

10:30–11:00 Coffee break

11:00–12:30 Poster Session II: Low-Resource, Indic

12:30–14:00 Lunch break

14:00–14:30 Oral Session D (Chair: Katsuhito Sudoh)

14:30–15:30 Planning Session for 2026

15:30–16:00 Coffee break

16:00-16:30 Best student paper award and closing remarks

16:30 End of conference

Important Notes

Oral and poster presentations will be on-site, oral presentations will be also streamed. Oral presentations will be 10-12 minutes, with 3-5 minutes for questions.

Oral sessions: Scientific papers will be presented in four oral sessions. Each paper is allotted a slot of 10-12 minutes, with 3-5 additional minutes for questions. Speakers attending virtually will be able to present through the Underline platform.

Poster sessions: System papers will be presented in two poster sessions arranged by shared tasks. Papers covering multiple tasks can be presented as distinct posters. Physical poster size is A0 portrait. Printing service is available on site: info from ACL 2025.

Video recordings: Speakers are invited to optionally share a link for a recorded video presentation regardless if they will be able to attend the conference in person or not. Please add the link to your max 10 min video recording for your paper by July 28, 2025 in this google sheet. Videos will be linked on the IWSLT program through the end of the IWSLT conference.

Oral Session A

• [1] The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence
  Authors: Marco Gaido | Sara Papi | Luisa Bentivogli | Alessio Brutti | Mauro Cettolo | Roberto Gretter | Marco Matassoni | Mohamed Nabih | Matteo Negri
• [2] Effects of automatic alignment on speech translation metrics
  Authors: Matt Post | Hieu Hoang

Oral Session B

• [3] HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation (Best student paper award)
  Authors: Amir Hussein | Cihan Xiao | Matthew Wiesner | Dan Povey | Leibny Paola Garcia Perera | Sanjeev Khudanpur
• [4] Quality-Aware Decoding: Unifying Quality Estimation and Decoding
  Authors: Sai Koneru | Matthias Huck | Miriam Exel | Jan Niehues

Oral Session C

• [5] Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models
  Authors: Minghan Wang | Thuy-Trang Vu | Yuxia Wang | Ehsan Shareghi | Gholamreza Haffari
• [6] SSR: Alignment-Aware Modality Connector for Speech Language Models
  Authors: Weiting Tan | Hirofumi Inaguma | Ning Dong | Paden D. Tomasello | Xutai Ma
  Links: [Video]
• [7] Streaming Sequence Transduction through Dynamic Compression
  Authors: Weiting Tan | Yunmo Chen | Tongfei Chen | Guanghui Qin | Haoran Xu | Chenyu Zhang | Benjamin Van Durme | Philipp Koehn Links: [Video]
• [8] Prompting LLMs: Length Control for Isometric Machine Translation
  Authors: Dávid Javorský | Ondřej Bojar | François Yvon
• [9] Swiss German Speech Translation and the Curse of Multidialectality
  Authors: Martin Bär | Andrea DeMarco | Gorka Labaka

Oral Session D

• [10] NUTSHELL: A Dataset for Abstract Generation from Scientific Talks
  Authors: Maike Züfle | Sara Papi | Beatrice Savoldi | Marco Gaido | Luisa Bentivogli | Jan Niehues
• [11] SparQLe: Speech Queries to Text Translation Through LLMs
  Authors: Amirbek Djanibekov | Hanan Aldarmaki

Poster Session I

Papers covering multiple shared tasks can be presented with multiple posters

• [1] Literary Translations and Synthetic Data for Machine Translation of Low-resourced Middle Eastern Languages
  Authors: Sina Ahmadi | Razhan Hameed | Rico Sennrich
• [2] Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning
  Authors: Giuseppe Attanasio | Sonal Sannigrahi | Ben Peters | André Filipe Torres Martins
• [3] NAVER LABS Europe Submission to the Instruction-following Track
  Authors: Beomseok Lee | Marcely Zanon Boito | Laurent Besacier | Ioan Calapodescu
• [4] Efficient Speech Translation through Model Compression and Knowledge Distillation
  Authors: Yasmin Moslem
• [5] KIT’s Offline Speech Translation and Instruction Following Submission for IWSLT 2025
  Authors: Sai Koneru | Maike Züfle | Thai Binh Nguyen | Seymanur Akti | Jan Niehues | Alexander Waibel
• [6] CUNI-NL@IWSLT 2025: End-to-end Offline Speech Translation and Instruction Following with LLMs
  Authors: Nam Luu | Ondřej Bojar
• [7] NAIST Offline Speech Translation System for IWSLT 2025
  Authors: Ruhiyah Faradishi Widiaputri | Haotian Tan | Jan Meyer Saragih | Yuka Ko | Katsuhito Sudoh | Satoshi Nakamura | Sakriani Sakti
• [8] NYA’s Offline Speech Translation System for IWSLT 2025
  Authors: Wenxuan Wang | Yingxin Zhang | Yifan Jin | Binbin Du | Yuke Li
• [9] Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025
  Authors: Dominik Macháček | Peter Polák
• [10] BeaverTalk: Oregon State University’s IWSLT 2025 Simultaneous Speech Translation System
  Authors: Matthew Raffel | Victor Agostinelli III | Lizhong Chen
  Links: [Slides]
• [11] CMU’s IWSLT 2025 Simultaneous Speech Translation System
  Authors: Siqi Ouyang | Xi Xu | Lei Li
• [12] MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task
  Authors: Jorge Iranzo-Sánchez | Javier Iranzo-Sanchez | Adrià Giménez Pastor | Jorge Civera Saiz | Alfons Juan
• [13] NAIST Simultaneous Speech Translation System for IWSLT 2025
  Authors: Haotian Tan | Ruhiyah Faradishi Widiaputri | Jan Meyer Saragih | Yuka Ko | Katsuhito Sudoh | Satoshi Nakamura | Sakriani Sakti
• [14] AppTek’s Automatic Speech Translation: Generating Accurate and Well-Readable Subtitles
  Authors: Frithjof Petrick | Patrick Wilken | Evgeny Matusov | Nahuel Unai Roselló Beneitez | Sarah Beranek

Poster Session II

• [15] CDAC-SVNIT submission for IWSLT 2025 Indic track shared task
  Authors: Mukund K. Roy | Karunesh Arora | Praveen Kumar Chandaliya | Rohit Kumar | Pruthwik Mishra
  Links: [Video]
• [16] Effectively combining Phi-4 and NLLB for Spoken Language Translation: SPRING Lab IITM’s submission to Low Resource Multilingual Indic Track
  Authors: Sankalpa Sarkar | Samriddhi Kashyap | Advait Joglekar | Srinivasan Umesh
• [17] HITSZ’s End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
  Authors: Xuchen Wei | Yangxin Wu | Yaoyin Zhang | Henglyu Liu | Kehai Chen | Xuefeng Bai | Min Zhang
• [18] IIITH-BUT system for IWSLT 2025 low-resource Bhojpuri to Hindi speech translation
  Authors: Bhavana Akkiraju | Aishwarya Pothula | Santosh Kesiraju | Anil Vuppala
  Links: [Video]
• [19] IWSLT 2025 Indic Track System Description Paper: Speech-to-Text Translation from Low-Resource Indian Languages (Bengali and Tamil) to English
  Authors: Sayan Das | Soham Chaudhuri | Dipanjan Saha | Dipankar Das | Sivaji Bandyopadhyay
  Links: [Video]
• [20] JU-CSE-NLP’s Cascaded Speech to Text Translation Systems for IWSLT 2025 in Indic Track
  Authors: Debjit Dhar | Soham Lahiri | Tapabrata Mondal | Sivaji Bandyopadhyay
  Links: [Video] [Slides]
• [21] ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task
  Authors: Josef Jon | Waad Ben Kheder | Andre Beyer | Claude Barras | Jean-Luc Gauvain
• [22] Bemba Speech Translation: Exploring a Low-Resource African Language
  Authors: Muhammad Hazim Al Farouq | Aman Kassahun Wassie | Yasmin Moslem
• [23] BUINUS at IWSLT: Evaluating the Impact of Data Augmentation and QLoRA-based Fine-Tuning for Maltese to English Speech Translation
  Authors: Filbert Aurelian Tjiaranata | Vallerie Alexandra Putra | Eryawan Presma Yulianrifat | Ikhlasul Akmal Hanif
• [24] GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task
  Authors: Chutong Meng | Antonios Anastasopoulos
• [25] Human-Evaluated Urdu-English Speech Corpus: Advancing Speech-to-Text for Low-Resource Languages
  Authors: Humaira Mehmood | Sadaf Abdul Rauf
• [26] JHU IWSLT 2025 Low-resource System Description
  Authors: Nathaniel Romney Robinson | Niyati Bafna | Xiluo He | Tom Lupicki | Lavanya Shankar | Cihan Xiao | Qi Sun | Kenton Murray | David Yarowsky
• [27] KIT’s Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization
  Authors: Zhaolin Li | Yining Liu | Danni Liu | Tuan Nam Nguyen | Enes Yavuz Ugan | Tu Anh Dinh | Carlos Mullov | Alexander Waibel | Jan Niehues
• [28] LIA and ELYADATA systems for the IWSLT 2025 low-resource speech translation shared task
  Authors: Chaimae Chellaf | Haroun Elleuch | Othman Istaiteh | D. Fortuné KPONOU | Fethi Bougares | Yannick Estève | Salima Mdhaffar
  Links: [Video]
• [29] QUESPA Submission for the IWSLT 2025 Dialectal and Low-resource Speech Translation Task
  Authors: John E. Ortega | Rodolfo Joel Zevallos | William Chen | Idris Abdulmumin
• [30] SYSTRAN @ IWSLT 2025 Low-resource track
  Authors: Marko Avila | Josep Crego
• [31] Kuvost: A Large-Scale Human-Annotated English to Central Kurdish Speech Translation Dataset Driven from English Common Voice
  Authors: Mohammad Mohammadamini | Daban Jaff | Sara Jamal | Ibrahim Ahmed | Hawkar Omar | Darya Sabr | Marie Tahon | Antoine Laurent
• [32] FFSTC 2: Extending the Fongbe to French Speech Translation Corpus
  Authors: D. Fortuné KPONOU | Salima Mdhaffar | Fréjus A. A. Laleye | Eugène Cokou Ezin | Yannick Estève
  Links: [Video]