Audio Classification Using CNN — An Experiment
CNN is best suited for images. Leveraging its power to classify spoken digit sounds with 97% accuracy.
Our eyes are best suited for looking. Our ears for hearing. If hypothetically, eyes were far more intelligent and quicker as compared to ears, wouldn’t it be more useful to send sound signals to our eyes for processing?
If sound frequencies could be turned into images in some manner and sent to eyes to differentiate we might be able to understand a larger range of frequencies. We might start understanding what dogs and dolphins say. We might hear the much discussed cosmic hum!
In the 1950s and 1960s David Hubel and Torsten Wiesel conducted experiments on the brain of mammals and suggested a model for how mammals perceive the world visually. Our research on vision has been going on since then. Out of such research was born a very powerful algorithm known as the Convolutional Neural Network (CNN).
