James B. Maxwell

Learn More
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(More)
ManuScore is a music notation-based, interactive music composition application, backed by a cognitively-inspired music learning and generation system. In this paper we outline its various functions, describe an applied composition study using the software, and give results from a study of listener evaluation of the music composed during the composition(More)
We investigate Musical Metacreation algorithms by applying Music Information Retrieval techniques for comparing the output of three off-line, corpus-based style imitation models. The first is Variable Order Markov Chains, a statistical model; second is the Factor Oracle, a pattern matcher; and third, MusiCOG, a novel graphical model based on perceptual and(More)
We propose a design and implementation for a music information database and query system, the MusicDB, which can be used for Music Information Retrieval (MIR). The MusicDB is implemented as a Java package, and is loaded in MaxMSP using the mxj external. The MusicDB contains a music analysis module, capable of extracting musical information from standard(More)
We present an empirical study investigating the hypothesis that listeners hold a bias against computer-composed music. Presented in part as a replication study, the proposed methodology seeks to improve upon weaknesses found in previous studies of the subject. Across two study periods, with approximately 60 subjects each, we failed to find evidence of a(More)
  • 1