TY - JOUR
KW - Application programming interfaces (API)
KW - Audio acoustics
KW - Automatic music transcription
KW - Discrete Fourier transform
KW - Discrete Fourier transforms
KW - Extraction
KW - Feature extraction
KW - Intangible cultural heritages
KW - Learning systems
KW - machine learning
KW - Mobile applications
KW - Mobile computing
KW - Polyphonic music
KW - Predicting models
KW - Sopele
KW - Supervised learning
KW - Supervised machine learning
KW - Traditional woodwind instrument
KW - Woodwind instruments
AU - Arian Skoki
AU - Sandi Ljubic
AU - Jonatan Lerga
AU - Ivan Stajduhar
AB - Sopela is a traditional hand-made woodwind instrument, commonly played in pair, characteristic to the Istrian peninsula in western Croatia. Its piercing sound, accompanied by two-part singing in the hexatonic Istrian scale, is registered in the UNESCO Representative List of the Intangible Cultural Heritage of Humanity. This paper presents an insight study of automatic music transcription (AMT) for sopele tunes. The process of converting audio inputs into human-readable musical scores involves multi-pitch detection and note tracking. The proposed solution supports this process by utilising frequency-feature extraction, supervised machine learning (ML) algorithms, and postprocessing heuristics. We determined the most favourable tone-predicting model by applying grid search for two state-of-the-art ML techniques, optionally coupled with frequency-feature extraction. The model achieved promising transcription accuracy for both monophonic and polyphonic music sources encompassed in the originally developed dataset. In addition, we developed a proof-of-concept AMT system, comprised of a client mobile application and a server-side API. While the mobile application records, tags and uploads audio sources, the back-end server applies the presented procedure for converting recorded music into a common notation to be delivered as a transcription result. We thus demonstrate how collecting and preserving traditional sopele music, performed in real-life occasions, can be effortlessly accomplished on-the-go.
BT - Pattern Recognition Letters
DA - dec
DO - 10.1016/j.patrec.2019.09.024
LA - English
N1 - Publisher: Elsevier B.V.
N2 - Sopela is a traditional hand-made woodwind instrument, commonly played in pair, characteristic to the Istrian peninsula in western Croatia. Its piercing sound, accompanied by two-part singing in the hexatonic Istrian scale, is registered in the UNESCO Representative List of the Intangible Cultural Heritage of Humanity. This paper presents an insight study of automatic music transcription (AMT) for sopele tunes. The process of converting audio inputs into human-readable musical scores involves multi-pitch detection and note tracking. The proposed solution supports this process by utilising frequency-feature extraction, supervised machine learning (ML) algorithms, and postprocessing heuristics. We determined the most favourable tone-predicting model by applying grid search for two state-of-the-art ML techniques, optionally coupled with frequency-feature extraction. The model achieved promising transcription accuracy for both monophonic and polyphonic music sources encompassed in the originally developed dataset. In addition, we developed a proof-of-concept AMT system, comprised of a client mobile application and a server-side API. While the mobile application records, tags and uploads audio sources, the back-end server applies the presented procedure for converting recorded music into a common notation to be delivered as a transcription result. We thus demonstrate how collecting and preserving traditional sopele music, performed in real-life occasions, can be effortlessly accomplished on-the-go.
PY - 2019
SP - 340
EP - 347
T2 - Pattern Recognition Letters
TI - Automatic music transcription for traditional woodwind instruments sopele
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85072880061&doi=10.1016%2fj.patrec.2019.09.024&partnerID=40&md5=6c8f0da0e86aefbe92e4cfe28e302e84
VL - 128
SN - 01678655 (ISSN)
ER -