My thesis project is on Audio Feature extraction, their classifcation and comparison.
I am unable to extract the audio features from the last 6months.
I just have an idea that may work.
The audio in any format is to be converted into pcm format and features like bandwidth, Zero Crossing Rate, Noise Frame Ratio, Pitch Strength and mel Frequency Cepctral Coefficients can be extracted from it. Then a data set is prepared using these features and then various audio classifiaction algoriths are applied to it.
Kindly help how can i proceed further and extract audio features?
Thanx
Although it is a very old post but maybe someone would reach here after googling. Now there are some very good toolkits to use :
This is probably too late to be of much help, but you should really look at the jmir project. It's a system for doing audio feature extraction and classification in Java. It's all open source and well documented.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With