Speech-related research has a wide range of applications. Most speech-related researches employ Mel-frequency cepstral coefficients (MFCCs) as acoustic features. However, finding the optimum number of MFCCs is an active research question. MFCC-based speech classification was performed for both vowels and words in the Bengali language. As for the classification model, deep neural network (DNN) with Adam optimizer was used. The performances were measured with five different performance metrics, namely confusion matrix, classification accuracy, area under curve of receiver operating characteristic (AUC-ROC), F${}_1$ score, and Cohen's Kappa with four-fold cross-validations at different number of MFCCs. All performance metrics gave the best score for 24/25 MFCCs; hence it is suggested that the optimum number of MFCCs should be 25, although many existing studies use only 13 MFCCs. Furthermore, it is verified that increasing the number of MFCCs yields better classification metrics with lower computational burden than the increment of hidden layers. Lastly, the optimum number of MFCCs obtained from this study was used in a more improved DNN model, from which 99% and 90% accuracies were achieved for vowel and word classification, respectively, and the vowel classification score outperformed state-of-the-art results.

In this paper, an automatic speech recognition system has been proposed for isolated Bangla word using Support vector machine with Dynamic time warping (DTW). For training purposes, we have collected data from 40 speakers for five different Bangla words. All the data was collected in a highly acoustic and noise-proof environment. Mel frequency cepstrum coefficients (MFCC's) are considered as static features from the speech signal. For dynamic features, first and second derivatives of MFCC are utilized. After determining feature vectors, a modified DTW method is proposed for feature matching. Finally, for classification Support Vector Machine (SVM) with Radial basis function (RBF) is utilized. The model is tested for 12 speakers and the recognition rate that we achieved is 86.08%.