KEIA
BMAT project researching content-auditing techniques intended to identify copyrighted material used by AI music systems.
Research
Papers, projects and labs working on AI music.
140 results
La inteligencia artificial generativa en la música y el derecho de autor colombiano
Legal research article on generative music AI under Colombian copyright and neighboring-rights law.
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
Research work examining music retrieval, music/audio representation learning.
Libretto: Giving LLM Agents a Sense of Musical Structure
Research work examining music generation, music retrieval.
LiveBand: Live Accompaniment Generation in the Audio Domain
Research work examining automatic accompaniment, evaluation benchmark.
LLark: A Multimodal Instruction-Following Language Model for Music
Research work examining music/audio understanding.
Local Multimodal Music Alignment from Global Supervision
Research work examining music retrieval, music/audio understanding.
Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing
Research work examining music generation, music/audio editing.
Machine learning and chord based feature engineering for genre prediction in popular Brazilian music
Study using chord-derived features and machine learning to predict genres in popular Brazilian music.
Machine Learning Solutions for Instrumental Music Generation
Soluções de aprendizado de máquina para geração de música instrumental
USP master's dissertation evaluating GAN, VAE and LSTM approaches for instrumental music generation.
MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations
Research work examining evaluation benchmark, music/audio understanding.
Magenta
Open-source Google research project exploring machine learning as a tool in creative music and art processes.
Magenta RealTime 2
Open-weights live music model and framework for low-latency, on-device interactive music generation.
Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
Research work examining audio generation, evaluation benchmark.
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning
Research work examining music/audio representation learning.
MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Research work examining evaluation benchmark, music retrieval.