1 / 30

Rule induction for expressive music performance modeling ISMIR Graduate School - October 2004

ahazan@iua.upf.es. Rule induction for expressive music performance modeling ISMIR Graduate School - October 2004. Amaury Hazan. Outline. Expressive Performance Modeling Model Descriptors Classical ML techniques ILP Techniques Results Further Work. Expressive Performance Modeling.

Download Presentation

Rule induction for expressive music performance modeling ISMIR Graduate School - October 2004

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. ahazan@iua.upf.es Rule induction for expressive music performance modelingISMIR Graduate School - October 2004 Amaury Hazan

  2. Outline • Expressive Performance Modeling • Model Descriptors • Classical ML techniques • ILP Techniques • Results • Further Work

  3. Expressive Performance Modeling • A jazz musician alterates strongly the score of the excerpt he performs • Example: Body And Soul

  4. Expressive Performance Modeling • For each note of a score, given a contextual description, predict expressive transformations. • 2 Aims: understand and generate

  5. 2. Model Descriptors • Current Note Descriptors • Note Duration • Note Metrical Strength (within a bar) • Local Context Descriptors • Previous and next note relative duration • Previous and next note relative pitch • Melodic Context Descriptors (ILP) • Narmour I/R representation • Considering note Neighbors • Performance Related: Tempo deviation

  6. Model Descriptors Duration Meter Strength

  7. Model Descriptors Next note relative pitch and duration Previous note relative pitch and duration Duration Meter Strength

  8. Model Descriptors: ILP Next note relative pitch and duration Previous note relative pitch and duration Duration Meter Strength Melodic Context

  9. Model Descriptors: ILP Next note relative pitch and duration Previous note relative pitch and duration Duration Meter Strength Neighbors local description Melodic Context

  10. Training Set • Body And Soul, Once I Loved, Like Someone in Love • 11 tempo deviations for each song • 5 slow • 1 nominal • 5 fast • Resulting Dataset: 1936 notes

  11. 3. Classical ML Techniques • Classification • Naive Bayes • Lazy Learning • Induction Trees • Boosting, Bagging • Regression • Model Trees • Support Vector Machines

  12. Classical ML Techniques: Target Classes • Duration Ratio, Onset Deviation, Energy • Classification • Discretization: • Duration Ratio: 9 classes • Onset Deviation: 7 classes • Energy: 3 classes • Regression

  13. 4. ILP Techniques • First-order logic rule induction • Use of extensive background knowledge • One can induce either very general theories (knowledge discovery) or generative models • ILP: Set of rules and Tree-based strategies

  14. ILP: Overview • Given: • Set of positive examples • Set of negative examples • Background Knowledge • Induce a set of rules: • That explains the positive examples • That does not cover the negative examples • That uses background knowledge concepts

  15. ILP: Set of Rules and Tree-based Theory • Set of rules • Sequential covering of the examples • Each rule is induced independently of the others (covering loop) • Tree-based Theory • First Order generalization of induction trees • Each full path of the tree is a rule

  16. Rule 2 Rule 1 Delegating Exceptions : Uncovered Examples • Positives left: No rule apply to these examples 270 examples are not covered by any rule in the model

  17. Rule 2 Rule 1 Delegating Exceptions : Intersecting Rules • Rule conflicts: Intersecting rules assign a different class to the same example 128 examples are covered by more than two intersecting rules

  18. ILP: Target Classes • Note to note transformations • Duration ratio with the score note (shorten, same, lengthen) • Onset deviation with the score note (advance, same, delay) • Energy of the performed note (soft, medium, loud) • Melody alterations • Ornamentation • Consolidation • None

  19. 4. Results • ILP: Rules with significant coverage • Classical ML techniques • Solution synthesis

  20. Results: ILP • Rules with significant coverage: S-1: [Pos cover = 12 Neg cover = 1] stretch(A,B,C,lengthen):- succ(C,D),melo(A,B,D,4,-1,-1,0,-1,1,nominal). ``Lengthen a note at an offbeat position if its successor is a quarter between two shorter notes, the former one being at the same pitch, the next one being lower, at a nominal tempo''

  21. Results: ILP S-2: [Pos cover = 21 Neg cover = 1] stretch(A, B, C, shorten) :- succ(C, D), succ(D, E), context(A, E, [nargroup(p, 1)|F]), context(A, C, [nargroup(p, 2)|F]). ``Shorten a note n if it belongs to a P Narmour group in second position and if note n+2 belongs to a P Narmour group in first position''

  22. Results: ILP A-1: [Pos cover = 232 Neg cover = 0] alteration(A, B, C, none) :- :- context(A, C, [nargroup(p, 2)|D]). ``Do not perform alteration of a note if it belongs to a P Narmour group in second position''

  23. Results: ILP A-2: [Pos cover = 8 Neg cover = 0] alteration(A, B, C, ornamentation) :- succ(C, D), context(A, D, [nargroup(d, 2)|E]), member(nargroup(ip, 1), E), context(A, C, [nargroup(vr, 3)|F]). ``Ornamentate a note if it belongs to a VR Narmour group in third position and if its successor belongs to D Narmour group in second position and to IP Narmour group in first position''

  24. Results: Classical ML techniques Duration Model

  25. Results: Solution Synthesis • Melody transformation (Model Tree)

  26. 5. Further Work • Fuzzy Logic • Intra note Expressive Descriptors • Solution Synthesis • Structure Level Knowledge • Players Interactions

  27. Intra note Expressive Description • High Level Intra note classes e.g. : attack(A, soft). sustain(A, vibrato).

  28. Solution Synthesis • Midi + controls: • Amplitude • Pitch • Audio synthesis • A/S/R construction

  29. Structure Level Knowledge • Performance note description considering • Local context • Melodic context • Song structure (e.g. ABABCC)

  30. Players Interactions • Considering other instruments scores • Chords/Tonality representation • Band model: Considering each player's expressive transformations

More Related