There are 6 repositories under audio-feature-extraction topic.
Java Implementation of the Sonopy Audio Feature Extraction Library by MycroftAI
Speaker recognition using Mel Frequency Cepstral Coefficients (MFCC) and Linde-Buzo-Gray (LBG) clustering algorithm
Urban Sound Annotation and Classification
Audio input -> real-time analysis -> OSC output. Takes in real-time audio, does feature extraction using smart algorithms then sends out OSC to be used in other programs.
Tooling and datasets for neural-network powered audio feature based synthesis
Scratch for experimenting with audio feature extraction.
Trained a CNN model to classify whale calls into an A-call or not
Convolutional-based supervised regression task for extracting high level timbral features from drums sound files, useful to condition a real time Neural Sound Synthesiser on continuous intuitive controls.
Various Neural Network Architectures for Supervised Tonic classification using the mridangam_stroke dataset, and supervised instrument classification on the TinySOL dataset.
Drum Samples Clustering, Audio feature extraction and clustering audio files using data visualization and dimensionality reduction (PCA).
Python Script to suggest the volume at which the music audio file needs to be played for better experience and feeling.
Developed a deep learning model using Multi-Layer Perceptron to recognize and classify speech signals into 6 distinct emotions. Extracted 160 audio features, enabling the model to detect emotions with around 75% accuracy on the training set. Implemented the model on a Streamlit dashboard.
Text-independent speaker identification system based on GMM
AudioInspect is an app that extracts audio features from uploaded audio files or audio files in a specified folder, providing insights into the characteristics of the audio.
GTZAN Music genre classification using Logistic regression and SVM.
Generation of music playlists based on audio features analysis using Essentia and the MusAV dataset
A simple music feature extractor for Deep Learning models
Twenor is a conceptual platform designed to assist artists with advanced tools for audio classification, cover art creation, and music management. Envisioned to integrate neural network-based classification, customizable cover art design, and Recordbox XML support, Twenor aims to streamline and enhance the music production workflow—all for free.
Created as part of Audio and Music processing lab assignment. Extracts and analyses features from an audio collection, and creates playlists based on various descriptors. Can create playlists based on music similarity too.
An Object Oriented framework for easy feature logging on ChucK systems
Haskell and I are giving it another go.
Node changed their float implementation and broke Meyda. This was a repro
A server to host JAMS audio feature extraction data
High level audio features for Javascript