Guitar Music Transcription (GMT)

Date of Publication

2009

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Rafael Cabredo

Defense Panel Member

Jocelyn Cu

Karlo Campos

Abstract/Summary

Existing systems for regular music transcription are limited to external information for accurate transcriptions. An example of this is the use of midi file formats along with guitar synthesizers and a format that can store additional music information. The output of this research is a prototype for an application tool that handles the basic issues of music transcription. The tool lessened transcription inaccuracies by using feature extraction techniques that can detect and distinguish notes more accurately. The features that the research focused on are the pitch and duration of the note. To compute the basic music features the following approach were implemented: onset detection using edge detection filter frequency estimation using fast Fourier transform duration estimation using a histogram and assigning a note value to the most current note and note classification. All manipulated features are passed to the system's interpreter, which is then formatted to MusicXML file format. The prototype has an accuracy of 97% for pitch detection and 79% for note duration estimation.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU19861

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1 v. (various foliations) leaves : 28 cm. + one computer optical disc.

Keywords

Arrangement (Music)

This document is currently not available here.

Share

COinS