Md. Rakibul Hasan investigated the effect of Mel-frequency cepstral coefficient (MFCC) variation on convolutional neural network-based speech classification. He collected isolated vowel and word samples from Bengali speech and extracted MFCC features. A CNN model was trained on the MFCC data and achieved higher accuracy for vowel recognition compared to word recognition. Analysis showed vowels had less MFCC variation than words, contributing to their better classification performance by the CNN model.