INTERSPEECH 2008
9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Context-Dependent Phone Models and Models Adaptation for Phonotactic Language Recognition

Mohamed Faouzi BenZeghiba, Jean-Luc Gauvain, Lori Lamel

LIMSI, France

The performance of a PPRLM language recognition system depends on the quality and the consistency of phone decoders. To improve the performance of the decoders, this paper investigates the use of context-dependent instead of context-independent phone models, and the use of CMLLR for model adaptation. This paper also discusses several improvements to the LIMSI 2007 NIST LRE system, including the use of a 4-gram language model, score calibration and fusion using the FoCal Multi-class toolkit (with large development data) and better decoding parameters such as phone insertion penalty. The improved system is evaluated on the NIST LRE-2005 and the LRE-2007 evaluation data sets. Despite its simplicity, the system achieves for the 30s condition a Cavg of 2.4% and 1.6% on these data sets, respectively.

Full Paper

Bibliographic reference.  BenZeghiba, Mohamed Faouzi / Gauvain, Jean-Luc / Lamel, Lori (2008): "Context-dependent phone models and models adaptation for phonotactic language recognition", In INTERSPEECH-2008, 313-316.