Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification

Behind human voice production, a complex biological mechanism generates and modulates sound. Recent research has explored machine-learning (ML) techniques to analyze singing-voice characteristics. However, the classification efficiency reported in such research works suggests the possibility of impr...

Full description

Saved in:
Bibliographic Details
Main Authors: Tales Boratto, Gabriel de Oliveira Costa, Alexsandro Meireles, Anna Klara Sá Teles Rocha Alves, Camila M. Saporetti, Matteo Bodini, Alexandre Cury, Leonardo Goliatt
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Signals
Subjects:
Online Access:https://www.mdpi.com/2624-6120/6/1/9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087920621322240
author Tales Boratto
Gabriel de Oliveira Costa
Alexsandro Meireles
Anna Klara Sá Teles Rocha Alves
Camila M. Saporetti
Matteo Bodini
Alexandre Cury
Leonardo Goliatt
author_facet Tales Boratto
Gabriel de Oliveira Costa
Alexsandro Meireles
Anna Klara Sá Teles Rocha Alves
Camila M. Saporetti
Matteo Bodini
Alexandre Cury
Leonardo Goliatt
author_sort Tales Boratto
collection DOAJ
description Behind human voice production, a complex biological mechanism generates and modulates sound. Recent research has explored machine-learning (ML) techniques to analyze singing-voice characteristics. However, the classification efficiency reported in such research works suggests the possibility of improvement. In addition, there is also scope for further improvement through the application of still under-utilized optimization techniques. Thus, the present article proposes a novel approach that leverages the Differential Evolution (DE) algorithm to optimize hyperparameters within three selected ML models, with the aim of classifying singing-voice registers i.e., chest, mixed, and head registers). To develop the present study, a dataset of 350 audio files encompassing the three aforementioned registers was constructed. Then, the TSFEL Python library was employed to extract 14 pieces of temporal information from the audio signals for subsequent classification by the employed ML models. The obtained findings demonstrated that the Extreme Gradient Boosting model, optimized with DE, achieved an average classification accuracy of 97.60%, thus indicating the efficacy of the proposed approach for singing-voice register classification.
format Article
id doaj-art-b109e04bd1f34b3990f5a7a589ec71e9
institution DOAJ
issn 2624-6120
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Signals
spelling doaj-art-b109e04bd1f34b3990f5a7a589ec71e92025-08-20T02:43:07ZengMDPI AGSignals2624-61202025-02-0161910.3390/signals6010009Machine Learning with Evolutionary Parameter Tuning for Singing Registers ClassificationTales Boratto0Gabriel de Oliveira Costa1Alexsandro Meireles2Anna Klara Sá Teles Rocha Alves3Camila M. Saporetti4Matteo Bodini5Alexandre Cury6Leonardo Goliatt7Graduate Program in Computational Modeling, Federal University of Juiz de Fora, Juiz de Fora 36036-900, MG, BrazilDepartment of Mechatronics Engineering, Federal Institute of Southeast Minas Gerais, Juiz de Fora 36080-001, MG, BrazilDepartment of Languages and Literature, Federal University of Espírito Santo, Vitória 29075-910, ES, BrazilGraduate Program in Nursing, Federal University of Juiz de Fora, Juiz de Fora 36036-900, MG, BrazilDepartment of Computational Modeling, Polytechnic Institute, Rio de Janeiro State University, Nova Friburgo 22000-900, RJ, BrazilDipartimento di Economia, Management e Metodi Quantitativi, Università degli Studi di Milano, Via Conservatorio 7, 20122 Milano, ItalyDepartment of Computational and Applied Mechanics, Federal University of Juiz de Fora, Juiz de Fora 36036-900, MG, BrazilDepartment of Computational and Applied Mechanics, Federal University of Juiz de Fora, Juiz de Fora 36036-900, MG, BrazilBehind human voice production, a complex biological mechanism generates and modulates sound. Recent research has explored machine-learning (ML) techniques to analyze singing-voice characteristics. However, the classification efficiency reported in such research works suggests the possibility of improvement. In addition, there is also scope for further improvement through the application of still under-utilized optimization techniques. Thus, the present article proposes a novel approach that leverages the Differential Evolution (DE) algorithm to optimize hyperparameters within three selected ML models, with the aim of classifying singing-voice registers i.e., chest, mixed, and head registers). To develop the present study, a dataset of 350 audio files encompassing the three aforementioned registers was constructed. Then, the TSFEL Python library was employed to extract 14 pieces of temporal information from the audio signals for subsequent classification by the employed ML models. The obtained findings demonstrated that the Extreme Gradient Boosting model, optimized with DE, achieved an average classification accuracy of 97.60%, thus indicating the efficacy of the proposed approach for singing-voice register classification.https://www.mdpi.com/2624-6120/6/1/9singing registersmachine learningdifferential evolutionclassificationoptimization
spellingShingle Tales Boratto
Gabriel de Oliveira Costa
Alexsandro Meireles
Anna Klara Sá Teles Rocha Alves
Camila M. Saporetti
Matteo Bodini
Alexandre Cury
Leonardo Goliatt
Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
Signals
singing registers
machine learning
differential evolution
classification
optimization
title Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
title_full Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
title_fullStr Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
title_full_unstemmed Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
title_short Machine Learning with Evolutionary Parameter Tuning for Singing Registers Classification
title_sort machine learning with evolutionary parameter tuning for singing registers classification
topic singing registers
machine learning
differential evolution
classification
optimization
url https://www.mdpi.com/2624-6120/6/1/9
work_keys_str_mv AT talesboratto machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT gabrieldeoliveiracosta machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT alexsandromeireles machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT annaklarasatelesrochaalves machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT camilamsaporetti machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT matteobodini machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT alexandrecury machinelearningwithevolutionaryparametertuningforsingingregistersclassification
AT leonardogoliatt machinelearningwithevolutionaryparametertuningforsingingregistersclassification