https://github.com/sabaudian/music_genre_classification_project
Audio Pattern Recognition project - Music Genres Classification
https://github.com/sabaudian/music_genre_classification_project
artificial-intelligence audio-analysis audio-classification audio-processing genre-classification genres-classification k-nearest-neighbours k-nn machine-learning music-genre-classification music-information-retrieval neural-network preprocessing preprocessing-data python random-forest random-forest-classification svm svm-classifier
Last synced: about 1 month ago
JSON representation
Audio Pattern Recognition project - Music Genres Classification
- Host: GitHub
- URL: https://github.com/sabaudian/music_genre_classification_project
- Owner: Sabaudian
- License: mit
- Created: 2023-02-18T15:21:09.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-25T12:37:09.000Z (8 months ago)
- Last Synced: 2024-11-14T16:11:38.097Z (3 months ago)
- Topics: artificial-intelligence, audio-analysis, audio-classification, audio-processing, genre-classification, genres-classification, k-nearest-neighbours, k-nn, machine-learning, music-genre-classification, music-information-retrieval, neural-network, preprocessing, preprocessing-data, python, random-forest, random-forest-classification, svm, svm-classifier
- Language: Python
- Homepage:
- Size: 1.33 GB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Music Genre Classification Project
This repository is based on the recognition of musical genres through supervised and unsupervised learning.
## Plugins:
- numpy: https://numpy.org
- librosa: https://librosa.org/doc/latest/index.html
- matplotlib: https://matplotlib.org
- pydub: https://pypi.org/project/pydub/
- pandas: https://pandas.pydata.org
- scikit-learn: https://scikit-learn.org/stable/
```
$ pip install -r requirements.txt
```
## Information:
the dataset used for built this project is the notorious GTZAN dataset, recovered from kaggle (_**link to database:** https://www.kaggle.com/datasets/andradaolteanu/gtzan-dataset-music-genre-classification_).
In the **utils** directory,
there are all that classes used for preprocessing the dataset and performing data augmentation
(I did not use the csv file available at the previous link, I built my own).
- **_features_computation:_** computation of the various features to extract from audio files.
- _**features_extractions:**_ extraction of the computed features to a csv file in a proper directory.
- _**features_visualizations:**_ visualization of the single audio signals and the visualization of the various extracted features with a confrontation of the different genres.
- _**prepare_dataset:**_ check the duration of audio files and perform data augmentation (30s long file -> ten 3s long chunk).
Then we have the core classes of the project:
- _**main:**_ main class of the project that calls all the other.
- _**genres_ul_functions:**_ performs k-means clustering and then performs its evaluation.
- **_genres_sl_functions:_** performs various classification algorithms (Neural Network, Random Forest, K-Nearest Neighbors, Support Vector Machine) and evaluate their performances with confusion matrix, roc curve and metrics (accuracy, F1-score,...).
- **_plot_functions:_** used for defining all the plot functions.
- **_constants:_** contains all the constants used in the project.
## Performace Summary:
| | MULTILAYER PERCEPTRON | RANDOM FOREST | K-NEAREST NEIGHBORS | SUPPORT VECTOR MACHINE |
| - | --------------------- | ------------- | ------------------- | ---------------------- |
| ACCURACY | 84.80 | 79.33 | 89.80 | 89.40 |
| F1-SCORE | 0.85 | 0.79 | 0.90 | 0.89 |
| EXECUTION TIME (sec) | 63.72 | 52.76 | 7.73 | 21.40 |