EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Evaluating the Aurora Connected Digit Recognition Task -- A Bell Labs Approach

Mohamed Afify, Hui Jiang, F. Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran

Bell Labs, Lucent Technologies, USA

Connected digit recognition has always been an ideal task for fundamental research in speech recognition due to its low complexity and potential applicaitons. In Bell Labs we have developed a number of techniques targeting directly or indirectly at connected digit recognition. For the Aurora task, we study a few such algorithms for the entire spectrum of the issues, including feature extraction, context-dependent digit modeling, minimum classification error acoustic modeling, unsupervised noise compensation, and utterance verification. We show how each component contributes to the reduction of digit recognition and verification errors. Average over all three test sets we obtained 84.6% and 91.3% digit accuracies for clean- and multi-condition training, respectively. This represents an average of 48.6% error rate reduction when compared to the official Aurora baseline results.

Full Paper

Bibliographic reference.  Afify, Mohamed / Jiang, Hui / Korkmazskiy, F. / Lee, Chin-Hui / Li, Qi / Siohan, Olivier / Soong, Frank K. / Surendran, Arun C. (2001): "Evaluating the Aurora connected digit recognition task -- a bell labs approach", In EUROSPEECH-2001, 633-636.