mlsanityData to 13 Oct 2026

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task

arXiv 2107.06959 ↗First posted 14 Jul 2021cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities, tasks and languages. First, we leverage general-purpose multilingual modules pretrained with large amounts of unlabelled and labelled data. We further enable knowledge transfer from the text task to the speech task by training two tasks jointly. Finally, our multilingual model is finetuned on speech translation task-specific data to achieve the best translation results. Experimental results show our system outperforms the reported systems, including both end-to-end and cascaded based approaches, by a large margin. In some translation directions, our speech translation results evaluated on the public Multilingual TEDx test set are even comparable with the ones from a strong text-to-text translation system, which uses the oracle speech transcripts as input.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

18 of 21 references.

References · 18

  1. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,916
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,979
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
  5. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,033
  6. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  7. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  8. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 500
  9. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 468
  10. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 456
  11. 2019Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debatescited by 114
  12. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
6 more
  1. 2018Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddingscited by 83
  2. 2020CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpuscited by 57
  3. 2021Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Taskcited by 54
  4. 2017Learning Joint Multilingual Sentence Representations with Neural Machine Translationcited by 52
  5. 2020A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Taskscited by 51
  6. 2019Multilingual End-to-End Speech Translationcited by 37

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3.

6 papers.

  1. 2022LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducerscited by 10
  2. 2023ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translationcited by 9
  3. 2023NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Trackcited by 9
  4. 2022Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translationcited by 8
  5. 2023Multilingual Speech-to-Speech Translation into Multiple Target Languagescited by 5
  6. 2022The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Taskcited by 3