Mitsuyo Hashida

On Evaluating Systems for Generating Expressive Music Performance: the Rencon Experience

Abstract Research into music generation and into emulating human musical competence has attracted much attention in the field of computer science. In general, the results of academic research should be verified by assessing ‘objective effectiveness’, which is often represented by a ‘recognition ratio’. Although ‘objective effectiveness’ is also a requirement for research in music generation, it is meaningless unless subjective requisites are also satisfied. However, it is not easy for researchers to execute subjective evaluations within their individual endeavours. To address this difficulty within the research area of computer systems for generating expressive music performances, the Performance Rendering Contest (Rencon) was created. This is an international competition in which entrants present computer systems and the performances generated are graded, and has been held in conjunction with related international conferences. This paper presents an overview of Rencon history, highlighting the evaluative motivation of each contest. In addition, we discuss the possibilities of a new scientific research field in which future Rencons may play a role.

jPop-E: an assistant system for performance rendering of ensemble music

This paper introduces jPop-E (java-based PolyPhrase Ensemble), an assistant system for the Pop-E performance rendering system. Using this assistant system, MIDI data including expressive tempo changes or velocity control can be created based on the users musical intention. Pop-E (PolyPhrase Ensemble) is one of the few machine systems devoted to creating expressive musical performances that can deal with the structure of polyphonic music and the users interpretation of the music. A well-designed graphical user interface is required to make full use of the potential ability of Pop-E. In this paper, we discuss the necessary elements of the user interface for Pop-E, and describe the implemented system, jPop-E.

Strategy-acquisition system for video trading card game

Behavior and strategy of computers(COM) have recently attracted considerable attention with regards to video games, with the development of hardware and the spread of entertainment on the Internet. Previous studies have reported strategy-acquisition schemes for board games and fighting games. However, there have been few studies dealing with the scheme applicable for video Trading Card Games (video TCG). We present an automatic strategy-acquisition system for video TCGs. The proposed strategy-acquisition system uses a sampling technique, Action predictor, and State value function for obtaining rational strategy from many unobservable variables in a large state space. Computer simulations, where our agent played against a Rule-based agent, showed that a COM with the proposed strategy-acquisition system becomes stronger and more adaptable against an opponents strategy.

Crossing colorful communication: a system for enhancing sound communication

We describe an interactive multimedia application called crossing colorful communication (C.C.C), players of which can enjoy collaborative and interactive media control by speaking or making sound. Players of C.C.C. fire visual bullets, the direction and the size of which are determined by the pitch and the intensity of each players voice. When bullets collide on the screen, visual and sound effects are created. Players of C.C.C. can enjoy a new style of communication powered by mediatechnologies.

On cognition of musical grouping: relationship between the listeners’ schema type and their musical preference

We assume that there are various musical groupings of perceptions according to the degree of schemata and there are two dominant music grouping schemata; (a) accent-oriented grouping schema and (b) phrasing schema (musical expression referred to as the Rainbow type). In order to verify these hypotheses, we investigated how listeners’ groupings change when the inner voice of Beethoven’s Piano Sonata “Pathetique” was replaced with chords. We eventually succeeded in identifying three listening groups; those who have a strong (a) schema (type A), those whose (a) is prior to (b) (type AF), and those whose (b) is prior to (a) while paying attention to their inner voice (type FAI). We verified that type A listeners prefer Rap music, Rock music, listening in a lively place, listening to party music, and listening to lyrics, while type FAIlisteners prefer Bach, Chopin, and listening alone and quietly.