Baselight

Music Features

A dataset to test your music tagging model

@kaggle.insiyeah_musicfeatures

Loading...
Loading...

About this Dataset

Music Features

Context

A music genre is a conventional category that identifies pieces of music as belonging to a shared tradition or set of conventions. It is to be distinguished from musical form and musical style. The features extracted from these waves can help the machine distinguish between them.

Content

The features in this dataset are extracted from the dataset provided here which consists of 1000 audio tracks each 30 seconds long. It contains 10 genres, each represented by 100 tracks. The tracks are all 22050Hz Mono 16-bit audio files in .wav format. The code used to extract features is at this GitHub repo. Features are extracted using libROSA library.

Acknowledgements

The credits to this dataset go to MARSYAS.

Inspiration

Due to the artistic nature of music, the classifications are often arbitrary and controversial, and some genres may overlap. Train a model and know to which genre your favourite piece of music belong to.

Tables

Data

@kaggle.insiyeah_musicfeatures.data
  • 259.32 KB
  • 1000 rows
  • 30 columns
Loading...

CREATE TABLE data (
  "filename" VARCHAR,
  "tempo" DOUBLE,
  "beats" BIGINT,
  "chroma_stft" DOUBLE,
  "rmse" DOUBLE,
  "spectral_centroid" DOUBLE,
  "spectral_bandwidth" DOUBLE,
  "rolloff" DOUBLE,
  "zero_crossing_rate" DOUBLE,
  "mfcc1" DOUBLE,
  "mfcc2" DOUBLE,
  "mfcc3" DOUBLE,
  "mfcc4" DOUBLE,
  "mfcc5" DOUBLE,
  "mfcc6" DOUBLE,
  "mfcc7" DOUBLE,
  "mfcc8" DOUBLE,
  "mfcc9" DOUBLE,
  "mfcc10" DOUBLE,
  "mfcc11" DOUBLE,
  "mfcc12" DOUBLE,
  "mfcc13" DOUBLE,
  "mfcc14" DOUBLE,
  "mfcc15" DOUBLE,
  "mfcc16" DOUBLE,
  "mfcc17" DOUBLE,
  "mfcc18" DOUBLE,
  "mfcc19" DOUBLE,
  "mfcc20" DOUBLE,
  "label" VARCHAR
);

Data 2genre

@kaggle.insiyeah_musicfeatures.data_2genre
  • 67.1 KB
  • 200 rows
  • 30 columns
Loading...

CREATE TABLE data_2genre (
  "filename" VARCHAR,
  "tempo" DOUBLE,
  "beats" BIGINT,
  "chroma_stft" DOUBLE,
  "rmse" DOUBLE,
  "spectral_centroid" DOUBLE,
  "spectral_bandwidth" DOUBLE,
  "rolloff" DOUBLE,
  "zero_crossing_rate" DOUBLE,
  "mfcc1" DOUBLE,
  "mfcc2" DOUBLE,
  "mfcc3" DOUBLE,
  "mfcc4" DOUBLE,
  "mfcc5" DOUBLE,
  "mfcc6" DOUBLE,
  "mfcc7" DOUBLE,
  "mfcc8" DOUBLE,
  "mfcc9" DOUBLE,
  "mfcc10" DOUBLE,
  "mfcc11" DOUBLE,
  "mfcc12" DOUBLE,
  "mfcc13" DOUBLE,
  "mfcc14" DOUBLE,
  "mfcc15" DOUBLE,
  "mfcc16" DOUBLE,
  "mfcc17" DOUBLE,
  "mfcc18" DOUBLE,
  "mfcc19" DOUBLE,
  "mfcc20" DOUBLE,
  "label" BIGINT
);

Share link

Anyone who has the link will be able to view this.