2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Multilingual End-to-End Speech Translation

      Preprint

      , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In this paper, we propose a simple yet effective framework for multilingual end-to-end speech translation (ST), in which speech utterances in source languages are directly translated to the desired target languages with a universal sequence-to-sequence architecture. While multilingual models have shown to be useful for automatic speech recognition (ASR) and machine translation (MT), this is the first time they are applied to the end-to-end ST problem. We show the effectiveness of multilingual end-to-end ST in two scenarios: one-to-many and many-to-many translations with publicly available data. We experimentally confirm that multilingual end-to-end ST models significantly outperform bilingual ones in both scenarios. The generalization of multilingual training is also evaluated in a transfer learning scenario to a very low-resource language pair. All of our codes and the database are publicly available to encourage further research in this emergent multilingual ST topic.

          Related collections

          Most cited references 4

          • Record: found
          • Abstract: not found
          • Article: not found

          Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            A neural interlingua for multilingual machine translation

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Unsupervised Word Segmentation from Speech with Attention

                Bookmark

                Author and article information

                Journal
                01 October 2019
                Article
                1910.00254

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                Accepted to ASRU 2019
                cs.CL eess.AS

                Theoretical computer science, Electrical engineering

                Comments

                Comment on this article