8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Language Detection by Neural Discrimination

Celestin Sedogbo (1), Sebastien Herry (1), Bruno Gas (2), Jean Luc Zarader (2)

(1) Thales Research & Technology, France
(2) Université Pierre et Marie Curie, France

We present in this paper a new method of language detection, which allows detection on telephone speech with short sentences (3 seconds). The modeling based on neural networks allows to model any language without acoustic decomposition of the speech signal. We applied our system for a detection task over 11 languages contained in the OGI MLTS corpus with 3 seconds duration signals. The results obtained with our design allow to detect languages with an average competitive rate of 77% for a real time application running on a P4 1.7GHz based platform.

Full Paper

Bibliographic reference.  Sedogbo, Celestin / Herry, Sebastien / Gas, Bruno / Zarader, Jean Luc (2004): "Language detection by neural discrimination", In INTERSPEECH-2004, 1561-1564.