This project focuses on detecting word spoken in the audio sample. We need to first train the program by recording repeated utterances of each digit in the dictionary. Then comes the analysis part : where, we need to separate ambient noises from the each word. A good acoustic model should be derived from speech characteristics that will enable the system to distinguish between the different words in the dictionary. Then we select a classification algorithm. We also need to build a UI(user interface) that displays the time domain plot of each detected word as well as the classified digit for the program.
Here is the video link for demo of our project: https://www.youtube.com/watch?v=veRKVuxq0Ks&t=0s