Preliminary Experiments on Unsupervised Word Discovery in Mboshi

Pierre Godard, Gilles Adda, Martine Adda-Decker, Alexandre Allauzen, Laurent Besacier, Hélène Bonneau-Maynard, Guy-Noël Kouarata, Kevin Löser, Annie Rialland, François Yvon


The necessity to document thousands of endangered languages encourages the collaboration between linguists and computer scientists in order to provide the documentary linguistics community with the support of automatic processing tools. The French-German ANR-DFG project Breaking the Unwritten Language Barrier (BULB) aims at developing such tools for three mostly unwritten African languages of the Bantu family. For one of them, Mboshi, a language originating from the “Cuvette” region of the Republic of Congo, we investigate unsupervised word discovery techniques from an unsegmented stream of phonemes. We compare different models and algorithms, both monolingual and bilingual, on a new corpus in Mboshi and French, and discuss various ways to represent the data with suitable granularity. An additional French-English corpus allows us to contrast the results obtained on Mboshi and to experiment with more data.


DOI: 10.21437/Interspeech.2016-886

Cite as

Godard, P., Adda, G., Adda-Decker, M., Allauzen, A., Besacier, L., Bonneau-Maynard, H., Kouarata, G., Löser, K., Rialland, A., Yvon, F. (2016) Preliminary Experiments on Unsupervised Word Discovery in Mboshi. Proc. Interspeech 2016, 3539-3543.

Bibtex
@inproceedings{Godard+2016,
author={Pierre Godard and Gilles Adda and Martine Adda-Decker and Alexandre Allauzen and Laurent Besacier and Hélène Bonneau-Maynard and Guy-Noël Kouarata and Kevin Löser and Annie Rialland and François Yvon},
title={Preliminary Experiments on Unsupervised Word Discovery in Mboshi},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-886},
url={http://dx.doi.org/10.21437/Interspeech.2016-886},
pages={3539--3543}
}