Feature Classification and Related Response in a Real-time Interactive Music SystemSkip other details (including permanent urls, DOI, citation information)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License. Please contact firstname.lastname@example.org to use this work in a way not covered by the license. :
For more information, read Michigan Publishing's access and usage policy.
Page 202 ï~~Feature Classification and Related ] Interactive Music i Robert Rowe M.I.T. Media Laborn Music & Cognition C 20 Ames St. Cambridge I rowe@ media-lab.media, Cypher is a real-time interactive music listener and a player. The listener listens to and a The player uses various algorithmic techniques ti The two halves are each hierarchical, where higi spans of time. The listener classifies for the playe and their behavior over time, and the player use. a cc aJ Cl Â~
Page 203 ï~~and simply related change in the inpu, combin complicated music. Specific sets of operations event according to connections made by the us transformations. Establishing such a connectic extracted from the input, the transformation to applied to the event, and the result of the operz Let us look at the listener's analysis by beginn order analysis places each incoming MIDI eve featurespace, a space framed by the following loudness, density, attack speed, duration, and
Page 204 ï~~chord formation, deceleration, glissando gei diminuendo, transposition, etc. Level 2 gene transformation modules; control variables re be changed according to the nature of the in] the current state of the variable. For exampl to accelerate its input more or less than it at feature found by the listener, and the accelei listener listens to a player. The player can be the output of Cypher's own player. Sending the input of the listener causes composition from a controlled feedback loon: the slaver