Modeling prosody for language identification on read and spontaneous speech

This paper deals with an approach to automatic language identification using only prosodic modeling. The actual approach for language identification focuses mainly on phonotactics because it gives the best results. We propose here to evaluate the relevance of prosodic information for language identification with read studio recording, as in our previous experiment (Rouas, J.L. et al., Proc. Eusipeo'02, 2002), and spontaneous telephone speech. For read speech, experiments were performed on the five languages of the MULTEXT database (Campione, E. and Veronis, J., Proc. ICSLP'98, p.3163-6, 1998). On the MULTEXT corpus, our prosodic system achieved an identification rate of 79 % on the five languages discrimination task. For spontaneous speech, experiments are made on the ten languages of the OGI multilingual telephone speech corpus (Muthusamy, Y.K. et al., Proc. ICSLP'92, 1992). On the OGI MLTS corpus, the results are given for language pair discrimination tasks, and are compared with results from F. Cummins et al. (Technical Report idsia-07-99, Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano, CH, 1999). In conclusion, if our prosodic system achieves good performance on read speech, it might not take into account the complexity of spontaneous speech prosody.