W2: The International Conference on Spoken Language Translation (IWSLT)

Marcello Federico, Alexander Waibel, Jiatao Gu, Kevin Knight, Will Lewis, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Marco Turchi

Description Schedule External Website
Live Session 1: Jul 9 (16:00-20:30 GMT)
Live Session 2: Jul 10 (00:00-01:00 GMT)
Live Session 3: Jul 10 (16:00-17:10 GMT)
The 17th International Conference on Spoken Language Translation (IWSLT) is an annual scientific conference for the study, development and evaluation of spoken language translation technology: speech-to-text, speech-to-speech translation, simultaneous and consecutive translation, speech dubbing, cross-lingual communication including all multimodal, emotional, para-linguistic, and stylistic aspects and their applications in the field. The conference organizes evaluations and workshop sessions around challenge areas, and presents scientific work and system descriptions.

Time (PDT) Event Speakers
July 9, 9:00 AM-9:15 AM Foreword/Introduction Marcello Federico/Alex Waibel
July 9, 9:15 AM-10:15 AM Keynote + Q&A Klaus Welle
July 9, 10:15 AM-11:15 AM Findings of IWSLT 2020 + Q&A Sebastian Stüker et al.
July 9, 11:30 AM-12:30 PM Panel Offline Speech Translation Marco Turchi et al.
July 9, 12:30 PM-1:30 PM Panel Simultanous ST Jiatao Gu et al.
July 9, 5:00 PM-6:00 PM Panel Open Domain MT Ajay Nagesh et al.
July 10, 9:00 AM-9:10 AM Opening remarks Marcello Federico
July 10, 9:10 AM-10:10 AM Panel of experts Alex Waibel
You can open the livestream video and in a separate window.

Recorded Livestream (July 9)

Pre-recorded Talks


Adapting End-to-End Speech Recognition for Readable Subtitles

Danni Liu


CASIA’s System for IWSLT 2020 Open Domain Translation

Qian Wang


Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System

Pinzhen Chen


CUNI Neural ASR with Phoneme-Level Intermediate Step for Non-Native SLT at IWSLT 2020

Peter Polák


Deep Blue Sonics’ Submission to IWSLT 2020 Open Domain Translation Task

Enmin Su


DiDi Labs’ End-to-end System for the IWSLT 2020 Offline Speech TranslationTask

Arkady Arkhangorodsky


Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Maury Courtland


ELITR Non-Native Speech Translation at IWSLT 2020

Dominik Macháček


End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning

Nikhil Kumar Lakumarapu


End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning

Hou Jeung Han


End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020

Marco Gaido


From Speech-to-Speech Translation to Automatic Dubbing

Marcello Federico


Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWS

Nikhil Saini


How Human is Machine Translationese? Comparing Human and Machine Translations of Text and Speech

Koel Dutta Chowdhury


Is 42 the Answer to Everything in Subtitling-oriented Speech Translation?

Alina Karakanta


ISTIC's Neural Machine Translation System for IWSLT’2020

You Pan


Joint Translation and Unit Conversion for End-to-end Localization

Prashant Mathur


KIT’s IWSLT 2020 SLT Translation System

Thanh-Le Ha


LIT Team's System Description for Japanese-Chinese Machine Translation Task in IWSLT 2020

Yimeng Zhuang


NAIST's Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task

Ryo Fukuda


Neural Simultaneous Speech Translation Using Alignment-Based Chunking

Evgeny Matusov


Octanove Labs' Japanese-Chinese Open Domain Translation System

Masato Hagiwara


ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020

Laurent Besacier


OPPO’s Machine Translation System for the IWSLT 2020 Open Domain Translation Task

Tingxun Shi


Re-translation versus Streaming for Simultaneous Translation

Colin Cherry


SRPOL's System for the IWSLT 2020 End-to-End Speech Translation Task

Tomasz Potapczyk


Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University

Parnia Bahar


The AFRL IWSLT 2020 Systems: Work-From-Home Edition

Jeremy Gwinnup


The HW-TSC Video Speech Translation System at IWSLT 2020

Minghan Wang


The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task

Raúl Vázquez


Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation

Felix Schneider


University of Tsukuba’s Machine Translation System for IWSLT20 Open Domain Translation Task

Hongyi Cui


Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task

Xiang Li