GAUSSIAN BACKEND DESIGN FOR OPEN-SET LANGUAGE DETECTION

This paper proposes a new approach to the challenging open-set language detection task. Most state-of-the-art approaches make use of data sources with several out-of-set languages to model such languages. In the proposed approach, no additional data from out-of-set languages is required, only date from the target languages is used. Experiments are conducted using the LRE-05 and the LRE-07 evaluation data sets with the 30s condition. A C-avg of 4.5% and 3.4% is obtained on these data set, respectively. These results are comparable with other reported results.