This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.
","abstract_html":"<p>This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture <em>char-rnn</em>. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.</p>","abstract_has_math":false,"creators":["Hannum, Andrew"],"institution":null,"degree_name":"M.S.","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Mario A. Lopez, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-01-01T08:00:00Z","date_published":"2018-01-01T08:00:00Z","updated_at":"2026-07-24T02:03:12Z","subjects":["Artificial intelligence","Generative music","Jazz improvisation","Machine learning","Neural network","Recurrent neural network","Artificial Intelligence and Robotics","Computer Sciences","Music Pedagogy"],"languages":["en"],"rights":["Copyright is held by the author. User is responsible for all copyright compliance.
"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.du.edu/etd/1532","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Mario A. Lopez, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Hannum, Andrew"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-01-08T08:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence","Generative music","Jazz improvisation","Machine learning","Neural network","Recurrent neural network","Artificial Intelligence and Robotics","Computer Sciences","Music Pedagogy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright is held by the author. User is responsible for all copyright compliance.
"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.du.edu/etd/1532"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.
"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["RNN-Based Generation of Polyphonic Music and Jazz Improvisation"]}]}],"canonical_facts":{"dc:contributor":["Mario A. Lopez, Ph.D."],"dc:creator":["Hannum, Andrew"],"dc:date.available":["2019-01-08T08:00:00Z"],"dc:description.abstract":["This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.
"],"dc:format":["application/pdf"],"dc:identifier":["https://digitalcommons.du.edu/etd/1532"],"dc:language":["en"],"dc:rights":["Copyright is held by the author. User is responsible for all copyright compliance.
"],"dc:subject":["Artificial intelligence","Generative music","Jazz improvisation","Machine learning","Neural network","Recurrent neural network","Artificial Intelligence and Robotics","Computer Sciences","Music Pedagogy"],"dc:title":["RNN-Based Generation of Polyphonic Music and Jazz Improvisation"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["M.S."]},"updated_at":"2026-07-24T02:03:12Z"}