I am looking help for my project for which I need C++ (or any other language) libraries useful for extraction of sound wave features like frequency, loudness, pitch and orientation. Using these features I want to make attention in a humanoid robot simulator .


3 Answers 3


From the ones I've been using I can recommend:

  • YAAFE - very pleasant to work with in Python
  • ESSENTIA - another one I like particularly due to Python integration
  • aubio
  • Aquila - friend of mine used it extensively and he likes it a lot

Recently I came across this paper and I believe that this should perfectly answer your question.

Moffat D. et al - An Evaluation of Audio Feature Extraction Toolboxes

They do provide a detailed comparison based on:

  • Amount of features available
  • Ease of usage
  • Output format of the features
  • Computational efficiency

They tested following libraries:

  • Aubio
  • Essentia
  • jAudio
  • Librosa
  • LibXtract
  • Marsyas
  • Meyda
  • MIR Toolbox
  • Timbre Toolbox

I can highly recommend librosa (python), for its intuitive API and excellent scikit-learn integration, which is useful for quickly using extracted features in a machine learning pipeline).

Check out some examples: introduction, scikit-learn integration demo.

  • 1
    $\begingroup$ First link (to librosa) is now broken. $\endgroup$
    – Cesar
    Aug 26, 2017 at 10:04


  • $\begingroup$ @Downvoter: Care to explain yourself? $\endgroup$
    – sobek
    Dec 10, 2015 at 20:59
  • 1
    $\begingroup$ I'm not the downvoter, but I think it's because this is a link-only answer, which we prefer to avoid on all *.SE sites. Care to give a sentence on WHY those toolboxes might help the OP? $\endgroup$
    – Peter K.
    Dec 12, 2015 at 17:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.