Course Description

Generating and understanding music presents a major challenge to artificial intelligence.  This class will focus on the problems of representing musical knowledge, and of learning how to understand and reproduce a style.  This interdisciplinary class is aimed both at computer science students who wish to delve into issues of knowledge representation and machine learning, and at music students who wish to learn computational techniques that can be applied to music.  Projects will be done in groups containing both musicians and computer scientists.

Prerequisites

This is an interdisciplinary course, and both music and computer science students will be able to contribute.  Therefore there are separate prerequisites for music students and computer science students.  For computer science students, the prerequisites are CS181 or CS182 and the ability to read music; for music students, Music 154, Music 157x or equivalent.  The prerequisites are flexible, and may be waived in particular cases by permission of instructor.

Enrollment in the course is limited; if necessary, preference will be given to students with more background.

Teaching Staff

Professor: Avi Pfeffer
Office: Maxwell Dworkin 251
Office Hours: Thursday 4-5

TF: Emir Kapanci
Office: Maxwell Dworkin 217
OH: TBA

TF: Chris Thorpe
Office Maxwell Dworkin 238
OH:  TBA

Calendar Notes

Wednesday, September 7th: class will meet in Maxwell Dworkin 323
Monday, October 6th: no class due to Yom Kippur
Friday, October 10th: make-up class for Yom Kippur
Monday, October 13th: no class due to Columbus Day
Friday, October 24th: make-up class for ISMIR
Monday, October 27th: no class due to ISMIR conference
Wednesday, October 29th: no class due to ISMIR conference
Friday, October 31st: make-up class for ISMIR
Wednesday, November 26th: no class due to Thanksgiving

Requirements

The course will have three kinds of requirements: reading and participation, accounting for 30% of the grade, four homeworks (40%) and a final project (30%).  

A question will be assigned on the readings for each lecture.  The questions will be designed to lead you into thinking about the readings. A short, one paragraph answer will be expected, to be handed in at the beginning of the lecture in which the readings are discussed.  The reading and participation grade will be based on completing the reading and answering the question, and on participating in class discussion.

The homeworks will be done in large teams, consisting of both musicians and computer scientists.  It is expected that everyone will have something to contribute to the team.  Each team will make a presentation to the class about their approach to the problem, and also provide a written report including a statement of work detailing the contributions of each group member.

The final project will consist of an investigation by an individual or small group into a topic on the interface between AI and music.  Milestones will be set throughout the course.  The project will be due at the end of reading period.


Syllabus (subject to change)

M 9/15: introduction (Hiller&Isaacson)
W 9/17: ontologies of music (Selfridge-Field)
M 9/22: music file formats (Csele, Hewlett&Selfridge-Field, Bainbridge, Cahill, Recordare)
W 9/24: music corpora (Huron, Schaffrath)
M 9/29: optical music recognition (Bainbridge&Wijaya, Bainbridge&Carter)
W 10/1: HW1 presentations
W 10/8: pitch recognition (Bores,  Cheveigne&Kawahra)
F 10/10: note segmentation (Duxbury et al., Viitaniemi et al.)
W 10/15: rhythm tracking 1 (Dixon)
M 10/20: rhythm tracking 2 (Cemgil & Kappen)
W 10/22: polyphonic pitch recognition (Marolt, Sterein et al)
F 10/24: HW2 presentations
F 10/31: harmonic analysis (Winograd)
M 11/3: pattern in music (Simon&Sumner, Nevill-Manning&Witten)
W 11/5: hierarchical structure (Lerdahl&Jackendoff, Bod)
M 11/10: melodic structure (Narmour)
W 11/12: HW3 presentations
M 11/17: Melodic similarity (O'Maidin, Crawford et al)
W 11/19: Harmonization (Hornel&Menzel, Thorpe)
M 11/24: Composition and Improvisation (Cope, Thom)
M 12/1: Accompaniment (Raphael)
W 12/3: HW4 presentations
M 12/8: Performance (Arcos et al., Widmer)
W 12/10: Project presentations
M 12/15: Project presentations

Readings

Sources
MMoM: Machine Models of Music, Stephan M. Schwanauer and David A. Levitt editors, MIT Press, 1993.
BM: Beyond MIDI, Eleanor Selfridge-Field editor, MIT Press, 1997.
tPoM: The Psychology of Music, Diana Deutsch editor, 2nd edition, Elsevier 1999.
MS: Melodic Similarity: Concepts, Procedures and Applications, Walter B. Hewlett and Eleanor Selfridge-Field editors, MIT Press, 1998.

[Hiller & Isaacson] Lejaren Hiller and Leonard Isaacson, "Musical Composition with a High-Speed Digital Computer", MMoM.
[Selfridge-Field] Eleanor Selfridge-Field, "Describing Musical Information", BM.
[Csele] Mark Csele, "The WAV File Format", web page, http://www.technology.niagarac.on.ca/courses/comp630/WavFileFormat.html.
[Hewlett & Selfridge-Field] Walter B. Hewlett and Eleanor Selfridge-Field, with David Cooper, Brent A. Field, Kia-Chuan Ng and Peer Sitter, "MIDI", BM.
[Bainbridge] David Bainbridge, "Csound", BM.
[Cahill] Margaret Cahill, "The Translation of Finale's Enigma File Format for CPNView", MSc thesis, University of Limerick, 1998.
[Recordare] Recordare, "The MusicXML Tutorial", web page, http://www.musicxml.org/xml/musicxml-tutorial.pdf.
[Huron] David Huron, "Humdrum and Kern: Selective Feature Encoding", BM.
[Shaffrath] Helmut Schaffrath, "The Essen Associative Code: A Code for Folksong Analysis", BM.
[Bainbridge & Wijaya] David Bainbridge and K Wijaya, "Bulk Processing of Optically Scanned Music", Seventh International Conference on Image Processing and its Applications, 1999.
[Bainbridge & Carter] David Bainbridge and N. Carter, "Automatic Reading of Music Notation", in Handbook of Character Recognition and Document Image Analysis, World Scientific, 1997.
[Bores] Bores Signal Processing, "Introduction to DSP", web-based tutorial, http://www.bores.com/courses/intro.
[Cheveigne & Kawahra] Alain de Cheveigne and Hideki Kawahra, "YIN: A Fundamental Frequency Estimator for Speech Recognition and Thythm Quantization", Journal of the Acoustical Society of America, 111(4), 1917-1930, 2002.
[Duxbury et al.] C. Duxbury, M. Sandler and M.E. Davies, "A Hybrid Approach to Musical Note Onset Detection", 5th International Conference on Digital Audio Effects, 2002.
[Viitaniemi et al.] T. Viitaniemi, Klapuri, A. Eronen, "A Probabilistic Model for the Transcription of Single-Voice Melodies", Finnish Signal Processing Symposium, 2003.
[Dixon] Simon Dixon, "Automatic Extraction of Tempo and Beat from Expressive Performances", Journal of New Music Research, 30(1), 39-58, 2001.
[Cemgil & Kappen] A.T. Cemgil and B. Kappen, "Monte Carlo Methods for Tempo Tracking and Rhythm Quantization", Journal of Artificial Intelligence Research, 18, 45-81.
[Marolt] M. Marolt, "SONIC: Transcription of Polyphonic Piano Music with Neural Networks", Workshop on Current Research Directions in Computer Music, Barecelona, 2001.
[Sterian et al.] Andrew Sterian, Mary H. Simoni and Gregory H. Wakefield, "Model-Based Music Transcription", International Computer Music Conference, 1999.
[Winograd] Terry Winograd, "Linguistics and the Computer Analysis of Tonal Harmony", MMoM.
[Simon&Sumner] Herbert A. Simon and Richard K. Sumner, "Pattern in Music", MMoM.
[Nevill-Manning&Witten] C.G. Nevill-Manning and I.H. Witten, "Identifying Hierarchical Structure in Sequences: A Linear-Time Algorithm", Jounral of Artificial Intelligence Research, 7, 67-82, 1997.
[Lerdahl&Jackendoff] Fred Lerdahl and Ray Jackendoff, "An Overview of Hierarchical Structure in Music", MMoM.
[Bod] Rens Bod, "A Unified Model of Structural Organization in Language and Music", Journal of Artificial Intelligence Research, 17, 289-308, 2002.
[Narmour] Eugene Narmour, "Hierarchical Expectation and Musical Style", tPoM.
[O'Maidin] Donncha O'Maidin, "A Geometrical Algorithm for Melodic Difference", MS.
[Crawford et al.] Tim Crawford, Costas S. Iliopoulos and Rajeev Raman, "String Matching Techniques for Musical Similarity and Melodic Recognition", MS.
[Hornel&Menzel] Dominik Hornel and Wolfram Menzel, "Learning Musical Structure and Style with Neural Networks", Computer Music Journal 22(4), 44-62, 1998.
[Thorpe] Christopher A. Thorpe, "Application of Markov Models to Bach-style Chorale Harmonization", in progress.
[Cope] David Cope, "A Computer Model of Music Composition", MMoM.
[Thom] Belinda Thom, "Interactive Improvisational Music Companionship: A User-Modeling Approach", User-Modeling and User-Adapted Interaction Journal, in print.
[Raphael] Chris Raphael, "A Probabilistic Expert System for Automatic Musical Accompaniment", Journal of Computer and Graphical Statistics, 10(3), 487-512, 2001.
[Arcos et al.] Josep Lluis Arcos, Ramon Lopez de Mantaras and Xavier Serra, "Saxex: A Case-Based Reasoning System for Generating Expressive Musical Performances", Journal of New Music Research, 27(3), 194-210, 1998.
[Widmer] Gerhard Widmer, "Learning Expressive Performance: The Structure-Level Approach", Journal of New Music Research, 25, 179-205, 1996.