raaaouf/XAI_for_audio-music_classification
This repo contains the code for extracting explainable audio files from music by processing their Mel Spectrograms we used forlocal XAI: lIME, SHAP and for globale XAI: ALE
This project helps music professionals or researchers understand why an AI system classifies a music track into a specific genre. By inputting an audio file or its processed representation (like a Mel Spectrogram) and a trained music genre classification model, it outputs explanations that highlight which parts of the music (temporal or time-frequency) are most influential in the model's decision. This tool is designed for anyone needing to interpret the logic behind automated music genre predictions.
No commits in the last 6 months.
Use this if you need to understand the reasoning behind an AI's classification of music genres, helping to build trust or identify biases in your automated systems.
Not ideal if you are looking for a pre-packaged, user-friendly application for music classification without needing to delve into the underlying AI explanations or code implementation.
Stars
8
Forks
—
Language
Jupyter Notebook
License
—
Last pushed
Aug 29, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/raaaouf/XAI_for_audio-music_classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...