Speech technology for unwritten languages - Archive ouverte HAL Access content directly
Journal Articles IEEE/ACM Transactions on Audio, Speech and Language Processing Year : 2020

Speech technology for unwritten languages

(1) , (2) , (3) , (4) , (3) , (3) , (5) , (6) , (5) , (7, 8) , (3) , (3) , (3) , (9) , (9) , (10) , (9) , (4) , (9, 11)
1
2
3
4
5
6
7
8
9
10
11
Pierre Godard
Markus Müller
  • Function : Author
  • PersonId : 942224

Abstract

Speech technology plays an important role in our everyday life. Speech is, among others, used for human-computer interaction, including, for instance, 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 paper 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.

Dates and versions

hal-02480675 , version 1 (16-02-2020)

Identifiers

Cite

Odette Scharenborg, Laurent Besacier, Alan Black, Mark Hasegawa-Johnson, Florian Metze, et al.. Speech technology for unwritten languages. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, ⟨10.1109/TASLP.2020.2973896⟩. ⟨hal-02480675⟩
174 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More