Diffusion models have quickly become the go-to paradigm for generative
m...
Data is the lifeblood of modern machine learning systems, including for ...
An ideal music synthesizer should be both interactive and expressive,
ge...
Recent neural network-based language models have benefited greatly from
...
We propose a new method for training a supervised source separation syst...
Real-world data is high-dimensional: a book, image, or musical performan...
Automatic Music Transcription (AMT), inferring musical notes from raw au...
Automatic Music Transcription has seen significant progress in recent ye...
Score-based generative models and diffusion probabilistic models have be...
Classifier metrics, such as accuracy and F-measure score, often serve as...
We consider the problem of learning high-level controls over the global
...
To make music composition more approachable, we designed the first AI-po...
Generating musical audio directly with neural networks is notoriously
di...
Music relies heavily on self-reference to build structure and meaning. W...
Music relies heavily on repetition to build structure and meaning.
Self-...
Discovering and exploring the underlying structure of multi-instrumental...
The Variational Autoencoder (VAE) has proven to be an effective model fo...
We consider the problem of transcribing polyphonic piano music with an
e...