Music and Audio

More than Just Words Modeling Non-textual Characteristics of Podcasts

Reproducible research code for the experiments presented in our article Kara1k a karaoke dataset for cover song identification and singing voice analysis published at IEEE ISM 2017 ybayleISM2017

Code used in the article "SATIN A Persistent Musical Database for Music Information Retrieval" by Yann Bayle, Pierre Hanna and Matthias Robine in CBMI 2017. SATIN is a MIR dataset for reproducible research.

Song Popularity Prediction Using Machine Learning Algorithms yashrajkakkadsongpopularityprediction

A customizable HTML5 audio player for React.js

httpsgithubcomwayne391musicstructureanalysisinmatlab

headphones lead sheet datasets in various formats

Implementations for master thesis "Musical Instrument Recognition in Multi-Instrument Audio Contexts" with MedleyDB.

Introducing multi-channel U-Net for Music Source Separation trained using weighted multi-task loss. - vskadandale/multichannel-unet-bss

C++ library with accompanying toolkit for music information retrieval

Cover Song Identification with Keras

HF's ML for Audio study group

httpsgithubcomUrosBgdmir

Music Structure Analysis Framework

iJazzARTIST Intelligent Jazz Accompanist for Real-Time human-computer Interactive muSic improvisaTion ( B.Sc. Thesis )

httpsgithubcomtangkktangkkmirexace

A PCM audio stream output library that provides cross-browser compatibility.

httpsgithubcomtabahiWebSpeechAnalyzer

Use a Convolutional Neural Network to predict a instrument and the note being played susiexiaAI_Music

A synthesizer that uses pitch detection to choose candidates for granular synthesis or sampling.

Code for the paper "LLark A Multimodal Foundation Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

Todays Trending Values for EDM Production Contribute to sergreewhatbpm development by creating an account on GitHub

Official Implementation of "Multitrack Music Transformer" (ICASSP 2023) - salu133445/mmt

A collection of 174,154 multi-track piano-rolls

4th position solution to the MediaEval - The 2019 Emotion and Themes in Music using Jamendo - sainathadapa/mediaeval-2019-moodtheme-detection

Source code for "Transferring the Style of Homophonic Music Using Recurrent Neural Networks and Autoregressive Model"

A library for chaining together multiple audio dsp processors/generators, written in Rust!

Examples of integrating Zig and Wasm for audio and graphics on the web - ringtailsoftware/zig-wasm-audio-framebuffer

ISMIR 2020 Paper repo: Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm

The official implementation of "TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music"