The Continuator: Musical Interaction With Style - PowerPoint PPT Presentation

The Continuator: Musical Interaction With Style

Presented by Ching-Hua Chuan

ISE 575, Spring 2007, March 29, USC

• Real-time interactive musical instruments that are able to produce stylistically consistent music.
• The system learns music styles automatically, and is seamlessly integrated in the playing mode of the musicians.
• Interactive v.s. imitation systems

• Architecture
• Automatic learning and generation
• Prefix trees with indexing scheme
• Variable-order Markov models
• Reduction functions
• Polyphony and rhythm
• Interactive musical instrument
• Biasing Markov generation

Input seq # 2: {A B B C}

Input seq # 1: {A B C D}

1 2 3 4

Input seq. 1: {A B}

• continuation_list = {3, 7}
• randomly pick B

Start again with {A B B}

 continuation_list = {8}

Learned prefix trees

• Start again with {A B B C}
• no match
• continuation_list({B C}) = {4}

Learned seq. :{A B C D A B B C }

1 2 3 4 5 6 7 8

Ending seq = {A B B C D}

Less refined reduction function. (pitch region instead of pitch)

- learned: {PR1 PR1 PR2 PR3 PR5} - Input: {PR1 PR1 PR2}

- Continuation = {PR3}, which is G in this case.

• Hierarchy of reductions

- pitch * duration * velocity

- small pitch region * velocity

- small pitch regions

- large pitch regions

Cont’d

• No continuation is found.

learned

Input

• Polyphony: legato v.s. musical cluster
• Rhythm (jazz and popular music)

- Natural, linear, input rhythms

- Fixed metrical structure

chord

legato

Fixed metrical structure

• Weighting the nodes according to how they match the external input.

S=1, we get a musical automaton insensitive to the musical context,

S=0, we get a reactive system which generates the closest musical

elements to the external input it finds in the database.

Bernard Lubat

The Continuator and children

Gyorgy Kurtag

Claude Barthelemy

Video from http://www.csl.sony.fr/Research/Experiments/Continuator/index.php

• Let’s play with it!