Automatic difficulty level rating for guitar tablatures

• Main Authors: Go, Goldwin, Kim, Yoon Min, Shin, Hyeong Tak, Velarde, Jeromeio A.
• Format: text
• Language: English
• Published: Animo Repository 2016
• Subjects: Guitar music; Tablature (Music); Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/10738
• Institution: De La Salle University

This research tackles the problem of automating the ranking of a guitar tablature's di culty level. Building upon recent research, this project proposes several di culty features and investigates their in uence on a set of pre-rated set of pieces being used by an existing academic standard of music levels. The di culty features will be ranked according to their in uence on a music school's levelling criteria. Models for automatically rating tablature were built around these experiments with the goal of a web application that provides the di culty level of a tablature, with hopes of improving the ambiguous format that guitar tablatures present. The linear regression model chosen had an r-squared metric of 27.61% and was implemented in a tablature repository website.