Papers › KIT's Multilingual Speech Translation System for IWSLT 2023

KIT's Multilingual Speech Translation System for IWSLT 2023

8 Jun 2023arXiv:2306.05320archive 2025-07-28

Danni Liu, Thai Binh Nguyen, Sai Koneru, Enes Yavuz Ugan, Ngoc-Quan Pham, Tuan-Nam Nguyen, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, Jan Niehues

Many existing speech translation benchmarks focus on native-English speech in high-quality recording conditions, which often do not match the conditions in real-life use-cases. In this paper, we describe our speech translation system for the multilingual track of IWSLT 2023, which evaluates translation quality on scientific conference talks. The test condition features accented input speech and terminology-dense contents. The task requires translation into 10 languages of varying amounts of resources. In absence of training data from the target domain, we use a retrieval-based approach (kNN-MT) for effective adaptation (+0.8 BLEU for speech translation). We also use adapters to easily integrate incremental training data from data augmentation, and show that it matches the performance of re-training. We observe that cascaded systems are more easily adaptable towards specific target domains, due to their separate modules. Our cascaded speech system substantially outperforms its end-to-end counterpart on scientific talk translation, although their performance remains similar on TED talks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dannigt/kit-iwslt2023-multilingual officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationRetrievalTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections