2nd Workshop on Spoken Language Technologies for Under-Resourced Languages

Universiti Sains, Penang, Malaysia
May 3-5, 2010

Mo Piu Minority Language: Data Base, First Steps And First Experiments

Geneviève Caelen-Haumont (1), Brigitte Cortial (2), Christian Culas (3), Tran Tri Doi (4), Thom Dinh Hong (5), Xuyen Lê Thi (6), Hung Phan Luong (4,7), Thanh Nguyen Ngoc (5), Emmanuel Pannier (8), Vanessa Roux (2), Jean-Pierre Salmon (1), Alice Vittrant (2,9), Hoang Thi Vuong (5), Ly A Song (10)

(1) International Research Center MICA, Hanoi University of Technology, Vietnam
(2) Université de Provence, Aix-en-Provence, France
(3) Research Institute on Contemporary Southeast Asia (IRASEC – CNRS – MAEE), Bangkok,
(4) University of Social Sciences and Humanities, Hanoi, Vietnam
(4) University of Social Sciences and Humanities, Hanoi, Vietnam
(5) Department of Culture, Sport, and Tourism, Lao Cai Province, Vietnam
(6) Université Paris 7, Paris, France; (7) Institute of Linguistics, Hanoi, Vietnam
(8) Institute of Sociology, Vietnam Academy of Social Sciences, Hanoi, Vietnam
(9) LACITO, Paris, France; (10) Nam Thu Thuong (Mo Piu ethnic village), Vietnam

This paper is a first contribution about the Mo Piu language and culture. This ethnic minority is settled in the mountains of the North Vietnam. This culture being not documented at all at the international level, its language is said 'under-resourced' in the point of view of the automatic processing.

After a cultural, social and economical presentation of this minority, the paper focusses on the results of the first field ground undertaken in june 2009, and especially on the data basis, and the first experiments on the Mo Piu speech (method and preliminary results). The study in progression is concerning the domain of human recognition of melodic segments in order to try to find out 1° if this language is tonal or not 2° and if so, what are the tonal units.

Index Terms: Mo Piu, ethnic groups, under-resourced language, endangered language, data basis, prosody, tonal units.

Full Paper

Bibliographic reference.  Caelen-Haumont, Geneviève / Cortial, Brigitte / Culas, Christian / Doi, Tran Tri / Hong, Thom Dinh / Thi, Xuyen Lê / Luong, Hung Phan / Ngoc, Thanh Nguyen / Pannier, Emmanuel / Roux, Vanessa / Salmon, Jean-Pierre / Vittrant, Alice / Vuong, Hoang Thi / Song, Ly A (2010): "Mo Piu minority language: data base, first steps and first experiments", In SLTU-2010, 42-50.