Guitar Music Transcription (GMT)

• Main Authors: Chua, Earl Nichollson S., Hernandez, Rainier C., Lautchang, Wilbern J., Ong, Ryann T.
• Format: text
• Language: English
• Published: Animo Repository 2009
• Subjects: Arrangement (Music)
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/5939
• Institution: De La Salle University

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.