Abstract
Combined classifiers offer solution to the pattern classification problems which arise from variation of the data acquisition conditions, the signal representing the pattern to be recognized and classifier architecture itself. This paper will study the effect of classifier architecture on the overall performance of the Arabic Speech Recognition System. Five different architectures will be studied and comparison of their performance is conducted. It is found that the architecture based on ensemble approaches outperform the modular approaches. The best ensemble-based architecture gives 94% while the best modular-based gives 79.3% for the testing data.
Subscribe to:
Posts (Atom)
