Automatic music transcription for traditional woodwind instruments sopele

•Prospects of sopele woodwind instrument AMT are inspected on a newly acquired dataset.•Unwanted pitch variation is mitigated using DFT and supervised machine learning.•DFT-coupled RF and CNN models achieve F1=0.92 in the polyphonic setup.•A full-stack system for effortless music preservation of sop...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters Vol. 128; pp. 340 - 347
Main Authors: Skoki, Arian, Ljubic, Sandi, Lerga, Jonatan, Štajduhar, Ivan
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.12.2019
Elsevier Science Ltd
Subjects:
Algorithms
Applications programs
Automatic music transcription
Cultural heritage
Cultural resources
Discrete Fourier transform
Feature extraction
Frequency
Learning algorithms
Machine learning
Mobile computing
Model accuracy
Musical scores
Piercing
Pitch
Problem solving
Singing
Sopele
Traditional woodwind instrument
Transcription
Woodwind music
Sopele
Traditional woodwind instrument
Automatic music transcription
Discrete Fourier transform
Machine learning
ISSN:0167-8655, 1872-7344
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Prospects of sopele woodwind instrument AMT are inspected on a newly acquired dataset.•Unwanted pitch variation is mitigated using DFT and supervised machine learning.•DFT-coupled RF and CNN models achieve F1=0.92 in the polyphonic setup.•A full-stack system for effortless music preservation of sopele pieces is presented.•The system performs reasonably well for transcribing sopele traditional music pieces. 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2019.09.024