arXiv research

BacHMMachine harmonizes Baroque chorales using theory-driven principles and Hidden Markov Models.

Grading function evaluates Bach-style chorales, outperforming human experts.

Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature…

A new CNN approach for time series forecasting outperforms traditional RNNs.

We describe a generalization of the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) which is able to encode prior information that state transitions are more likely between "nearby" states. This is accomplished by defining a similarity function on the state space and scaling transition probabilities by pai…

Aug-Gen improves music generation by augmenting training data with model-produced examples.

Recurrent Neural Networks (RNNS) are now widely used on sequence generation tasks due to their ability to learn long-range dependencies and to generate sequences of arbitrary length. However, their left-to-right generation procedure only allows a limited control from a potential user which makes them unsuitable for int…

Hawksmoor's ceiling and Pantheon dome cofferings are explained using conformal mappings and Mercator's projection.

The paper improves polyphonic music models by extracting salient features.

Neural network generates music scores directly from polyphonic audio.

Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling …