Title
Audio-Based Guitar Tablature Transcription Using Multipitch Analysis And Playability Constraints
Abstract
This paper proposes a method of guitar tablature transcription from audio signals. Multipitch estimation and fingering configuration estimation are essential for transcribing tablatures. Conventional multipitch estimation methods, including latent harmonic allocation (LHA), often estimate combinations of pitches that people cannot play due to inherent physical constraints. Unplayable combinations of pitches are eliminated by filtering the results of LHA with three constraints. We first enumerate playable fingering configurations, and use them to suppress any undesirable combination of pitches. The optimal fingering configuration in each time frame is optimized to satisfy the need for temporal continuity by using dynamic programming. We use synthesized guitar sounds from MIDI data (ground truth) for evaluation. Experiments with them demonstrate the improvement of multipitch estimation by 5.9 points on average in F-measure and the transcribed tablatures are playable.
Year
DOI
Venue
2013
10.1109/ICASSP.2013.6637636
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
guitar tablature, fingering configuration, multipitch estimation, onset detection, music signal processing
Transcription (linguistics),Audio signal,Dynamic programming,Tablature,Pattern recognition,Computer science,MIDI,Filter (signal processing),Guitar,Speech recognition,Artificial intelligence,Audio signal processing
Conference
ISSN
Citations 
PageRank 
1520-6149
1
0.35
References 
Authors
5
5
Name
Order
Citations
PageRank
Kazuki Yazawa110.35
Daichi Sakaue252.12
Kohei Nagira3172.22
Katsutoshi Itoyama415131.35
Hiroshi G. Okuno52092233.19