ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Comparing different model configurations for language identification using a phonotactic approach

D. Matrouf, Martine Adda-Decker, Jean-Luc Gauvain, Lori Lamel

In this paper different model configurations for language identification using a phonotactic approach are explored. Identification experiments were carried out on the 11-language telephone speech corpus OGI-TS, containing calls in French, English, German, Spanish, Japanese, Korean, Mandarin, Tamil, Farsi, Hindi, and Vietnamese. Phone sequences output by one or multiple phone recognizers are rescored with language-dependent phonotactic models approximated by phone bigrams. The parameters of different sets of acoustic phone models were estimated using the 4-language IDEAL corpus. Sets of language-specific phonotactic models were trained using the training portion of the OGI-TS corpus. Error rates are significantly reduced by combining language-dependent and language-independent acoustic decoders, especially for short segments. A 9.9% LID error rate was obtained on the 11-language task using phonotactic models trained on spontaneous speech data. These results show that the phonotactic approach is relative insensitive to an acoustic mismatch between training and test conditions.


doi: 10.21437/Eurospeech.1999-100

Cite as: Matrouf, D., Adda-Decker, M., Gauvain, J.-L., Lamel, L. (1999) Comparing different model configurations for language identification using a phonotactic approach. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 387-390, doi: 10.21437/Eurospeech.1999-100

@inproceedings{matrouf99_eurospeech,
  author={D. Matrouf and Martine Adda-Decker and Jean-Luc Gauvain and Lori Lamel},
  title={{Comparing different model configurations for language identification using a phonotactic approach}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={387--390},
  doi={10.21437/Eurospeech.1999-100}
}