Robust spoken language identification using large vocabulary speech recognition

A robust, task independent spoken Language Identi cation (LID) system which uses a Large Vocabulary Continuous Speech Recognition (LVCSR) module for each language to choose the most likely language spoken is described. The acoustic analysis uses mean cepstral removal on mel scale cepstral coe cients to compensate for di erent input channels. The system has been trained on 5 languages: English, German, Japanese, Mandarin Chinese and Spanish using a subset of the Oregon Graduate Institute 11 language data base. The ve language results show 88% correct recognition for 50 second utterances without using con dence measures and 98 % correct with con dence measures without the robust front end. The recognition rate is 81 % correct for 10 second utterances without con dence measures and 93 % correct with con dence measures without the robust front end. Adding the robust front end improves the recognition rate approximately 3 % on the short utterances and 1 % for the long utterances. The best performance has been obtained for systems trained on phonetically hand labeled speech.