-1

I'm trying to develop an application to classify music in to probably favorite or not probably favorite by training a Neural network from music which are already marked as favorite by user himself. I never done audio analysis before so I know almost nothing about it. To make this an accurate classification model what features do I need to include in my dataset of music. eg:- decibel values , frequency values, length of the audio

thank you

Lakshith Nishshanke
  • 117
  • 7
  • 1
    you will probably want an encoding of the actual frequency domain of the music itself using an RNN in addition to these other features given you have enough data – modesitt May 04 '19 at 06:51
  • 1
    This is very close to a recommendation problem. The most likely to be classified as a favorite is probably also what would be the primarily recommendation – Jon Nordby May 04 '19 at 19:54

2 Answers2

2

Start by using the music feature extractors from Essentia. You can for instance use their commandline tool. This provides you with tons of low-level audio features (30+ types), as well rhythm (6+ feature types) and tonal (6+ features). You can also do the same with the Python bindings.

Jon Nordby
  • 5,494
  • 1
  • 21
  • 50
1

Spectrograms are a useful technique for visualising the spectrum of frequencies of a sound and how they vary during a very short period of time. You can use a similar technique known as Mel-Frequency Cepstral Coefficients (MFCC) as features for the dataset.

MFCC

You can use Librosa's mfcc() function which generates an MFCC from time series audio data to make the task a lot easier

Buddhika Bandara
  • 351
  • 1
  • 11