Audio feature optimization approach towards speaker authentication in banking biometric system
Szymon Zaporowski, Andrzej Czyżewski, Bożena Kostek · The Journal of the Acoustical Society of America · 2021
Experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination dentifying most meaningful Mel-Frequency Cepstral Coefficients representing speech excerpts prepared for their classification are presented and discussed. The parameterization was made using Mel Frequency Cepstral Coefficients, Delta MFCC and Delta MFCC. In the next stage, feature vectors were passed to the input of individual algorithms utilized to reduce the size of the vector by previously mentioned algorithms. The vectors prepared in this way have been used for classifying vocalic segments employing Artificial Neural Network (ANN) and Support Vector Machine (SVM). The classification results using both classifiers and methods applied for reducing the number of parameters were presented. The results of the reduction are also shown explicitly, by indicating parameters proven to be significant and those rejected by particular algorithms. Factors influencing the obtained results were considered, such as difficulties associated with obtaining the data set, and ts labeling. The broader context of banking biometrics research carried-out and the results obtained in this domain were also discussed. [Project No. POIR.01.01.01-0092/19 entitled: “BIOPUAP—A biometric cloud authentication system” is currently financed by the Polish National Centre for Research and Development (NCBR) from the European Regional Development Fund.]