CMU’s IWSLT 2022 Dialect Speech Translation System

Brian Yan, Patrick Fernandes, Siddharth Dalmia, Jiatong Shi, Yifan Peng, Dan Berrebbi, Xinyi Wang, Graham Neubig, Shinji Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

This paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems. We also augment the paired ASR data with pseudo translations via sequence-level knowledge distillation from an MT model and use these artificial triplet ST data to improve our end-to-end (E2E) systems. Our E2E models are based on the Multi-Decoder architecture with searchable hidden intermediates. We extend the Multi-Decoder by orienting the speech encoder towards the target language by applying ST supervision as hierarchical connectionist temporal classification (CTC) multi-task. During inference, we apply joint decoding of the ST CTC and ST autoregressive decoder branches of our modified Multi-Decoder. Finally, we apply ROVER voting, posterior combination, and minimum bayes-risk decoding with combined N-best lists to ensemble our various cascaded and E2E systems. Our best systems reached 20.8 and 19.5 BLEU on test2 (blind) and test1 respectively Without any additional MSA data, we reached 20.4 and 19.2 on the same test sets.

Original languageEnglish
Title of host publicationIWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference
EditorsElizabeth Salesky, Marcello Federico, Marta Costa-Jussa
PublisherAssociation for Computational Linguistics (ACL)
Pages298-307
Number of pages10
ISBN (Electronic)9781955917414
Publication statusPublished - 2022
Externally publishedYes
Event19th International Conference on Spoken Language Translation, IWSLT 2022 - Dublin, Ireland
Duration: 2022 May 262022 May 27

Publication series

NameIWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference

Conference

Conference19th International Conference on Spoken Language Translation, IWSLT 2022
Country/TerritoryIreland
CityDublin
Period22/5/2622/5/27

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'CMU’s IWSLT 2022 Dialect Speech Translation System'. Together they form a unique fingerprint.

Cite this