Skip to Main content Skip to Navigation
Conference papers

Innovative technologies for under-resourced language documentation: The BULB Project

Gilles Adda 1, 2 Martine Adda-Decker 3 Odette Ambouroue 4 Laurent Besacier 5, 6 David Blachon 7 Héì Ene Bonneau-Maynard 1 Elodie Gauthier 5 Pierre Godard 1 Fatima Hamlaoui 8 Dmitry Idiatov 4 Guy-Noël Kouarata 9 Lori Lamel 1 Emmanuel-Moselly Makasso 3 Annie Rialland 3 Sebastian Stuker 10 Mark van de Velde 4 François Yvon 1 Sabine Zerbian 11
1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 IMMI - Institut des Technologies Multilingues et Multimédias de l'Information
3 LPP - LPP - Laboratoire de Phonétique et Phonologie - UMR 7018
4 LLACAN - Langage, LAngues et Cultures d'Afrique Noire
5 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
LIG - Laboratoire d'Informatique de Grenoble
6 IUF - Institut Universitaire de France
7 LIG - Laboratoire d'Informatique de Grenoble
8 ZAS - Zentrum für Allgemeine Sprachwissenschaft [Berlin]
9 DDL - Dynamique Du Langage
10 KIT - Institute for Anthropomatics
11 Universität Stuttgart [Stuttgart]
Abstract : The project Breaking the Unwritten Language Barrier (BULB), which brings together linguists and computer scientists, aims at supporting linguists in documenting unwritten languages. In order to achieve this we will develop tools tailored to the needs of documentary linguists by building upon technology and expertise from the area of natural language processing, most prominently automatic speech recognition and machine translation. As a development and test bed for this we have chosen three less-resourced African languages from the Bantu family: Basaa, Myene and Embosi. Work within the project is divided into three main steps: 1) Collection of a large corpus of speech (100h per language) at a reasonable cost. After initial recording, the data is re-spoken by a reference speaker to enhance the signal quality and orally translated into French. 2) Automatic transcription of the Bantu languages at phoneme level and the French translation at word level. The recognized Bantu phonemes and French words will then be automatically aligned. 3) Tool development. In close cooperation and discussion with the linguists, the speech and language technologists will design and implement tools that will support the linguists in their work, taking into account the linguists' needs and technology's capabilities. The data collection has begun for the three languages. For this we use standard mobile devices and a dedicated software—LIG-AIKUMA, which proposes a range of different speech collection modes (recording, respeaking, translation and elicitation). LIG-AIKUMA 's improved features include a smart generation and handling of speaker metadata as well as respeaking and parallel audio data mapping.
Keywords : Language documentation automatic phonetic transcription unwritten languages automatic alignment
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download
https://hal.archives-ouvertes.fr/hal-01350124
Contributor : Laurent Besacier <>
Submitted on : Friday, July 29, 2016 - 4:48:10 PM
Last modification on : Monday, May 11, 2020 - 9:52:05 AM

File

Vignette du document
CCURL_BULB_2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01350124, version 1

Collections

CNRS | UNIV-PARIS7 | UNIV-PARIS3 | INALCO | UGA | LIG_TDCGE_GETALP | USPC | UNIV-PARIS-SACLAY | LPP | UNIV-LYON2 | LIMSI | DDL | SORBONNE-UNIVERSITE | LIG | POLYTECH-GRENOBLE | UDL

Citation

Gilles Adda, Martine Adda-Decker, Odette Ambouroue, Laurent Besacier, David Blachon, et al.. Innovative technologies for under-resourced language documentation: The BULB Project. Workshop CCURL 2016 - Collaboration and Computing for Under-Resourced Languages - LREC, May 2016, Portoroz, Slovenia. ⟨hal-01350124⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

1650

Files downloads

527

Contact

Informations

CCSD