O'Reilly logo

C# Machine Learning Projects by Yoon Hyup Hwang

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Audio features – MFCC

For this project, we are going to focus on a subset of features that the full dataset has. We are going to use Mel Frequency Cepstral Coefficients (MFCCs) and their statistical distributions as the features to our ML models. Simply put, MFCC is a representation of the sound spectrum and we will use its statistical distributions, kurtosis, skewness, min, max, mean, median, and standard deviation. If you look at the sample set you have downloaded from the previous step, you will see the columns are named according to the corresponding statistical distribution. We are going to first look at the distributions of each of these features. The following code snippet shows how we computed the quartiles for each feature:

foreach ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required