Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track (2306.07763v1)

Published 13 Jun 2023 in cs.CL

Abstract: This paper presents NAVER LABS Europe's systems for Tamasheq-French and Quechua-Spanish speech translation in the IWSLT 2023 Low-Resource track. Our work attempts to maximize translation quality in low-resource settings using multilingual parameter-efficient solutions that leverage strong pre-trained models. Our primary submission for Tamasheq outperforms the previous state of the art by 7.5 BLEU points on the IWSLT 2022 test set, and achieves 23.6 BLEU on this year's test set, outperforming the second best participant by 7.7 points. For Quechua, we also rank first and achieve 17.7 BLEU, despite having only two hours of translation data. Finally, we show that our proposed multilingual architecture is also competitive for high-resource languages, outperforming the best unconstrained submission to the IWSLT 2021 Multilingual track, despite using much less training data and compute.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. Findings of the IWSLT 2023 Evaluation Campaign. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023). Association for Computational Linguistics.
  2. Findings of the IWSLT 2022 evaluation campaign. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 98–157, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
  3. FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 1–29, Bangkok, Thailand (online). Association for Computational Linguistics.
  4. Common voice: A massively-multilingual speech corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4218–4222, Marseille, France. European Language Resources Association.
  5. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale. In Proc. Interspeech 2022, pages 2278–2282.
  6. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449–12460.
  7. Ankur Bapna and Orhan Firat. 2019. Simple, scalable adaptation for neural machine translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1538–1548, Hong Kong, China. Association for Computational Linguistics.
  8. Alexandre Berard. 2021. Continual learning in multilingual NMT via language-specific embeddings. In Proceedings of the Sixth Conference on Machine Translation, pages 542–565, Online. Association for Computational Linguistics.
  9. Efficient inference for multilingual neural machine translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8563–8583, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  10. Steven Bird. 2011. Bootstrapping the language archive: New prospects for natural language processing in preserving linguistic heritage. Linguistic Issues in Language Technology, 6(4).
  11. Speech resources in the Tamasheq language. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2066–2071, Marseille, France. European Language Resources Association.
  12. ON-TRAC consortium systems for the IWSLT 2022 dialect and low-resource speech translation tasks. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 308–318, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
  13. Siminchik: A speech corpus for preservation of southern quechua. ISI-NLP 2, page 21.
  14. Unsupervised Cross-Lingual Representation Learning for Speech Recognition. In Proc. Interspeech 2021, pages 2426–2430.
  15. Multilingual domain adaptation for NMT: Decoupling language and domain information with adapters. In Proceedings of the Sixth Conference on Machine Translation, pages 578–598, Online. Association for Computational Linguistics.
  16. No language left behind: Scaling human-centered machine translation. arXiv preprint arXiv:2207.04672.
  17. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29:3451–3460.
  18. The state and fate of linguistic diversity and inclusion in the NLP world. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
  19. Samu-xlsr: Semantically-aligned multimodal utterance-level cross-lingual speech representation. IEEE Journal of Selected Topics in Signal Processing, 16(6):1493–1504.
  20. Layer-wise analysis of a self-supervised speech representation model. In 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 914–921. IEEE.
  21. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186–191, Brussels, Belgium. Association for Computational Linguistics.
  22. Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 3935–3939, Reykjavik, Iceland. European Language Resources Association (ELRA).
  23. Multilingual tedx corpus for speech recognition and translation. In Proceedings of Interspeech.
  24. FST: the FAIR speech translation system for the IWSLT21 multilingual shared task. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 131–137, Bangkok, Thailand (online). Association for Computational Linguistics.
  25. Multilingual translation with extensible multilingual pretraining and finetuning. arXiv preprint arXiv:2008.00401.
  26. Attention is all you need. Advances in neural information processing systems, 30.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Edward Gow-Smith (10 papers)
  2. Alexandre Berard (20 papers)
  3. Marcely Zanon Boito (18 papers)
  4. Ioan Calapodescu (12 papers)
Citations (11)
View on Semantic Scholar