7th International Conference on Spoken Language Processing
September 16-20, 2002
In this paper, we evaluate our noise robust feature extraction algorithms on the Aurora 2 and the German part of Aurora 3. Several algorithms are introduced and evaluated to deal with the noisy speech signals including our previous noise robust techniques used with Aurora (2), and new approaches evaluated with Aurora 3. Since there exist some differences between the two databases, modifications of front-end modules are needed. For Aurora (2), the average error rate reduction is 47% for clean training and 12% for multicondition training compared with the new baseline with endpoint detection. In Aurora (3), we obtain 17%, 27% and 53% error rate reduction for the well-matched, medium-mismatched and high-mismatched cases, respectively.
Bibliographic reference. Cui, Xiaodong / Iseli, Markus / Zhu, Qifeng / Alwan, Abeer (2002): "Evaluation of noise robust features on the Aurora databases", In ICSLP-2002, 481-484.