ISCA Archive SLTU 2012
ISCA Archive SLTU 2012

MISTRAL+: dedicated tool for under-resourced languages analysis

Benoît Weber, Geneviève Caelen-Haumont, Do-Dat Tran, Binh Hai Pham

This paper presents MISTRAL+, a dedicated tool for the study of under-resourced languages. MISTRAL+ is the upgrated version of an automatic tool created in 2004 called MELISM. The entire process has been modified in order to simplify and enhance the study of under-resourced languages. MISTRAL+ is composed of two separated modules: MISTRAL_Praat a plugin integrated to the tool PRAAT, and MISTRAL_xls a VBA module. MISTRAL_Praat enables the creation of an approximation of the signal that is studied, it performs an automatic tonal annotation and exports all data in a xls standard file. Using MISTRAL_xls, the user is able to easily and quickly extract from the data generated by MISTRAL_praat the information he needs for his study. In the first part, MISTRAL+ and its main functionalities will be presented. In the second part, a closer look will be put on MISTRAL_praat. The third part will describe the second module MISTRAL_xls. The last part will present the study done using MISTRAL+ on the study of the Mio Pu, a vietnamese under-resourced language.

Index Terms: F0 range, Phonetic IPA labeling, automatic annotation and segmentation, tonal languages, expressive speech.


Cite as: Weber, B., Caelen-Haumont, G., Tran, D.-D., Pham, B.H. (2012) MISTRAL+: dedicated tool for under-resourced languages analysis. Proc. 3rd Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2012), 119-124

@inproceedings{weber12_sltu,
  author={Benoît Weber and Geneviève Caelen-Haumont and Do-Dat Tran and Binh Hai Pham},
  title={{MISTRAL+: dedicated tool for under-resourced languages analysis}},
  year=2012,
  booktitle={Proc. 3rd Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2012)},
  pages={119--124}
}