My abstract project is dedicated to the extraction of audio functions, their class and comparison.
I can’t extract audio functions from last 6 months.
I just have an idea that might work.
Sound in any format must be converted to pcm, and functions such as bandwidth, zero crosstalk, frame-to-noise ratio, pitch strength, and sword frequency can be extracted from it. Then the data set is prepared using these functions, and then various sound classification algorithms are applied to it.
Please help, how can I continue to work and extract audio functions?
Thanx
source
share