Speech technology for unwritten languages

Journal article (2020)

Authors

O.E. Scharenborg , Radboud Universiteit Nijmegen
Alan W. Black Carnegie Mellon University
Mark Hasegawa-Johnson University of Illinois at Urbana Champaign
Florian Metze Carnegie Mellon University
Graham Neubig Carnegie Mellon University
Sebastian Stueker Karlsruhe Institut für Technologie
Pierre Godard LIMSI, ele-de-France
M Mueller Karlsruhe Institut für Technologie
More Authors More Authors External organisation
Copyright: © 2020 O.E. Scharenborg, Laurent Besacier, Alan W. Black, Mark Hasegawa-Johnson, Florian Metze, Graham Neubig, Sebastian Stueker, Pierre Godard, M Mueller, More Authors
DOI
help_outline
https://doi.org/10.1109/TASLP.2020.2973896
Speech processing Automatic speech recognition Unsupervised learning Image retrieval Speech synthesis
More Info
expand_more

Published Date

2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

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.

Files

08998182.pdf
(.pdf | 3.04 Mb)