0

I am working on extracting features from an audio file to build a recommendation system.

So far I am able to extract tempo, beat-times, loudness and pitch class using librosa and ffmpeg.

My question how we can extract/detect features as Danceability, Energy, Acousticness, Speechiness, Valence without using Spotify API. Are there any libraries or algorithm using which we can do so.

Srinjoy Chatterjee
  • 11
  • I am voting to close this for the reason "**Seeking recommendations for books, tools, software libraries, and more**". [help/on-topic]: "Questions asking us to _recommend or find a book, tool, software library, tutorial or other off-site resource_ are off-topic for Stack Overflow as they tend to attract opinionated answers and spam. Instead, describe the problem and what has been done so far to solve it." – Random Davis Mar 23 '22 at 18:28
  • 1
    No. Do you understand how totally subjective those things are? And none of them has any standardized definition. I'm not convinced a machine COULD decide any of those. My guess is that Spotify is returning polling data that was created by human listeners. – Tim Roberts Mar 23 '22 at 18:31

1 Answers1

0

It is depending on Which API you are using to get the Audio Features. Currently, except for Spotify, we don't have other APIs to get the features like (Danceability, Energy, Acousticness, Speechiness, Valence).

Using essentia Package we can get the Danceability Feature.

Refer Deep learning music information retrieval

Delliganesh Sevanesan
  • 4,146
  • 1
  • 5
  • 15