The Mathematics and Music Lab (MML) at Michigan Technological University has developed a line of "functional quantizer" modules for the VCV Rack software modular synthesizer platform, allowing synthesizer players to tune oscillators to new musical scales based on mathematical functions.
Experimenting with Suno, a generative AI music platform, to create a podcast theme song reveals unexpected and unconventional results.
M2UGen introduces a framework for multi-modal music understanding and generation using large language models.
Computational models can effectively predict and analyze emotions in music, offering potential applications in therapy and music queuing.
Notochord is a deep probabilistic model for real-time MIDI performance, enabling interactive musical functions with low latency.
Advancements in OMR models for piano music recognition are crucial, with a focus on practicality and evaluation metrics.
Introducing DTTNet, a lightweight framework for music source separation with improved performance and reduced parameters.
A diffusion-based generative model is introduced for music synthesis and source separation, enabling total generation, partial generation, and source separation tasks simultaneously.
Notochord is a deep probabilistic model designed for real-time MIDI performance, enabling interactive musical functions with low latency.
Enhancing multi-instrument music transcription with MR-MT3 to mitigate instrument leakage.