Documents

  • 08998182

    Accepted author manuscript, 2.96 MB, PDF document

DOI

  • Odette Scharenborg
  • Laurent Besacier
  • Alan W. Black
  • Mark Hasegawa-Johnson
  • Florian Metze
  • Graham Neubig
  • Sebastian Stueker
  • Pierre Godard
  • M Mueller
  • More Authors

Speech technology plays an important role in our everyday life. Among others, speech is used for human-computer interaction, for instance for information retrieval and on-line shopping. In the case of an unwritten language, however, speech technology is unfortunately difficult to create, because it cannot be created by the standard combination of pre-trained speech-to-text and text-to-speech subsystems. The research presented in this article takes the first steps towards speech technology for unwritten languages. Specifically, the aim of this work was 1) to learn speech-to-meaning representations without using text as an intermediate representation, and 2) to test the sufficiency of the learned representations to regenerate speech or translated text, or to retrieve images that depict the meaning of an utterance in an unwritten language. The results suggest that building systems that go directly from speech-to-meaning and from meaning-to-speech, bypassing the need for text, is possible.

Original languageEnglish
Article number8998182
Pages (from-to)964-975
Number of pages12
JournalIEEE/ACM Transactions on Audio Speech and Language Processing
Volume28
DOIs
Publication statusPublished - 2020

    Research areas

  • Speech processing, automatic speech recognition, image retrieval, speech synthesis, unsupervised learning

ID: 71016802