Motivation

With the current explosion and quick expansion of music in digital formats, and the computational power of modern systems, research on machine learning and music is gaining increasing popularity. As complexity of the problems investigated by researchers on machine learning and music increases, there is a need to develop new algorithms and methods to solve these problems. The focus of this workshop is on machine learning for music generation.  MML2015 aims to build on the previous seven successful MML editions:  MML2008, MML2009, MML2010, MML2011, MML2012, MML2013, and MML2014.

Theme: Machine Learning for Music Generation

This year's edition of the International Workshop on Machine Learning and Music (MML2015) will be held in conjunction for the first time with the International Symposium on Electronic Art (ISEA2015).  ISEA is one of the world’s most prominent international arts and technology events, bringing together scholarly, artistic, and scientific domains in an interdisciplinary discussion and showcase of creative productions applying new technologies in art, interactivity, and electronic and digital media.

Machine learning holds great potential for realizing the dream of computational creativity in music.  For MML2015, in addition to general topics in music and machine learning, we warmly welcome contributions describing theory and applications of machine learning for the generation of music.  All contributions may use allotted presentation time to deliver a performance of creative outputs arising from music generated from models constructed by machine learning.

Important Dates

Abstract Submission Deadline: May 5, 2015

Acceptance Notification: May 25, 2015

Final abstracts due: June 26, 2015

Workshop: August 15, 2015

JMM Special Issue submissions due: October 16, 2015

Submissions of extended abstracts

Extended abstracts of two printed pages in LNCS format are welcome. A third additional page may be added for references.  Extended abstracts will be evaluated according to their originality and relevance to the workshop, and should include author names, affiliations, and contact information. Please note that, to encourage participation, the workshop will publish extended abstracts and not full papers. Contributions should be in PDF format and submitted to musmachlear@gmail.com. LNCS format details can be found here.

Journal Special Issue

Selected accepted extended abstracts from the MML2015 workshop will be invited to submit full papers to a Special Issue of the Journal of Mathematics and Music (planned publication date July 2016).

Registration

Workshop registration will be handled by the main conference, please check ISEA2015 for more details. 

Organizers

Rafael Ramirez, Universitat Pompeu Fabra, Spain

Darrell Conklin, University of the Basque Country, Spain

José Manuel Iñesta, University of Alicante, Spain

Program (proceedings)

Session 1 (chair Darrell Conklin) (9:30-11:10)

Genre-based melody generation through multi-objective genetic algorithms
José M. Iñesta, Pedro J. Ponce de León, Jorge Calvo-Zaragoza, and David Rizo

Analysis of analysis: importance of different musical parameters for Schenkerian analysis
Phillip B. Kirlin and Jason Yust

Computational generation and synthesis of jazz guitar ornaments using machine learning modeling
Sergio Giraldo and Rafael Ramirez

Knowledge representation and algorithmic composition with MultiDiGraphs
Vitor Guerra Rolla

 Multilabel classification of non-verbal communication of emotions

 Pauline Mouawad, Myriam Desainte-Catherine and Jean-Luc Rouas

Coffee (11:10-11:40)

Session 2 (chair José M. Iñesta) (11:40-13:00)

Predicting loudness levels and classifying dynamic markings in recorded music

Katerina Kosta, Rafael Ramirez, Oscar F. Bandtlow, Elaine Chew, and Sergio Giraldo

Chord sequence generation with semiotic patterns 

Darrell Conklin

 EEG Signal classification in a Brain-Computer Music Interface
 Zacharias Vamvakousis and Rafael Ramirez

Trance generation by transformation
Darrell Conklin and Louis Bigo

Can machines learn to compose the way humans do? on the potential for qualitative musical analysis
Arne Eigenfeldt