Hidden Markov Model Approach to Skill Analysis in Violin Bowing

Takenaka, H. (1995) Hidden Markov Model Approach to Skill Analysis in Violin Bowing. Masters thesis, University of Washington.

Full text not available from this repository.

Abstract

Human Skill is an ability to perform a given task precisely in a suitable period. Skill consists of two categories, mental skill and motor skill. Skill acquisition has been on of the most important research areas in the fields of robotics, rehabilitation, and sports. One such skill is violin bowing whose methods for teaching have changed little over the years. This thesis investigates the possible development of a bowing motion analysis and training system based on optical position tracking of arm movement and Hidden Markov Modeling (HMM) of the movement data. A HMM is used to descriminate between two different types of bowing motions recorded with an optical motion analysis system. <p> The results showed that the HMM is capable of discriminating Legato from Staccato bowing, but that standard training algorithms do not improve performance.

Item Type: Thesis (Masters)
Subjects: Z Other
Divisions: Department of Electrical Engineering
Depositing User: Jeffrey Herron
Date Deposited: 07 Jul 2015 21:24
Last Modified: 07 Jul 2015 21:24
URI: http://brl.ee.washington.edu/eprints/id/eprint/78

Actions (login required)

View Item View Item