HSMM

Hierarchical Sequential Memory for Music:
A Cognitively-Inspired Approach to Generative Music

We propose a new machine-learning framework called the Hierarchical Sequential Memory for Music, or HSMM. The HSMM is an adaptation of the Hierarchical Temporal Memory (HTM) framework, designed to make it better suited to musical applications. The HSMM is an online learner, capable of recognition, generation, continuation, and completion of musical structures.

Members: James Maxwell, Arne Eigenfeldt, Philippe Pasquier.

Papers & Posters:

  • Maxwell, J.B., Pasquier, P., Eigenfeldt, A. Hierarchical Sequential Memory for Music: A Cognitive Model, International Society for Music Information Retrieval, Kobe, 2009. PDF
  • Maxwell, J.B., Pasquier, P., Eigenfeldt, A. The Hierarchical Sequential Memory For Music: A Cognitively-Inspired Model for Music Learning and Composition, International Conference on Music Perception and Cognition, Seattle, 2010.