SPOKEN-DIGIT CLASSIFICATION USING ARTIFICIAL NEURAL NETWORK

Audio classification has been one of the most popular applications Artificial Neural Networks. This process is at center modern AI technology, such as virtual assistants, automatic speech recognition, and text-to-speech applications. There have studies about spoken digit its However, to best author's knowledge, very few works focusing on English recognition that implemented ANN done. In this study, authors utilized Mel-Frequency Cepstral Coefficients (MFCC) features audio recording Network (ANN) classifier recognize by speaker. The MNIST dataset was used training test data while Free-Spoken Digit Dataset additional validation data. model showed an F-1 score 99.56% accuracy for F1 81.92%