Stars
App to explore latent spaces of music collections
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
A curated reading list of research in Sparse Autoencoders, Feature Extraction and related topics in Mechanistic Interpretability
Official repository of the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization".
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Music Information Retrieval Feature Library for Extraction
Materials related to the "Humans at the Center of MIR" tutorial at ISMIR 2024, in San Franscisco
High-quality Text-to-Audio Generation with Efficient Diffusion Transformer
A curated list of audio-visual learning methods and datasets.
Code for ICMR 2024 paper "BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval"
Repository for CloserMusicDB, a collection of full length studio quality tracks annotated by a team of human experts.
Code implementation for the paper titled MusicLIME: Explainable Multimodal Music Understanding
The official GitHub page for the survey paper "Foundation Models for Music: A Survey".
Identify a song from a small recorded sample using audio fingerprinting over frequency domain.
Deep and online learning with spiking neural networks in Python