Improvisation and Learning
نویسنده
چکیده
This article presents a 2-phase computational learning model and application. As a demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase 1 of training, recurrent back-propagation trains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation. After each phase CHIME can interactively improvise with a human in real time.
منابع مشابه
Teaching Improvisation through Processes. Applications in Music Education and Implications for General Education
Improvisation is an articulated multidimensional activity based on an extemporaneous creative performance. Practicing improvisation, participants expand sophisticated skills such as sensory and perceptual encoding, memory storage and recall, motor control, and performance monitoring. Improvisation abilities have been developed following several methodologies mainly with a product-oriented persp...
متن کاملInteraction with Machine Improvisation
We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive comp...
متن کاملImprovisation Support using Thermoscore-Display
In this paper, we propose an improvisation support system that makes advice after a player hits the key via temperature sensation. Differ from conventional improvisation support system, it does not change the essential function of the instrument itself. To examine the effectiveness of the system, we carried out an experiment and compared it with the typical improvisation support system and the ...
متن کاملA Concurrent Constraints Factor Oracle Model for Music Improvisation
Machine improvisation and related style simulation problems usually consider building representations of time-based media data, such as music, either by explicit coding of rules or applying machine learning methods. Stylistic learning applies such methods to musical sequences in order to capture salient musical features and organize these features into a model. The Stylistic simulation process ...
متن کاملLearning and the Evolution of Melodic Complexity in Virtuoso Jazz Improvisation
Spontaneous musical improvisation in jazz depends upon a substantial cognitive scaffolding that enables the real-time generation of creative structures. This work describes a computational model that simulates sub-conscious learning processes through an evolutionary paradigm.
متن کاملImprovisation Planning and Jam Session Design using concepts of Flow Experience
We describe a model for improvisation design based on Factor Oracle automation, which is extended to perform learning and analysis of incoming sequences in terms of sequence variation parameters, namely replication, recombination and innovation. These parameters describe the improvisation plan and allow designing new improvisations or analysis and modification of plans of existing improvisation...
متن کامل