Automatic Page-Turner for Pianists With Wearable Motion Detector

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Creator: 

Mirazimzadeh, Seyed Ali

Date: 

2021

Abstract: 

Turning book pages is a simple act that readers do while reading. This simple act that we take for granted could be challenging when both hands are engaged in other tasks. In case that a pianist sight-read, using one hand for turning the music sheets can cause distraction or short delay in their performance. Previous studies predominantly utilized audio or video processing techniques for following the musicians' performance. We suggested a framework that uses wearable technologies as an alternative solution for solving page-turning problems. The proposed design recognizes the pianist's wrists oscillatory motion with accelerometer sensors and tries to sync them to digital music notes. This system uses dynamic time warping and cross-correlation methods to find the optimum alignment between actual and captured data and reducing time latency. Eventually, a heuristic decision model assesses the pianist's performance and decides to turn the digital music sheet at predefined points.

Subject: 

Computer Science

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Applied Science: 
M.App.Sc.

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Human-Computer Interaction

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).