Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection

Gala-Ureña, Agosto de la; Romero-González, Julio-Alejandro; Assaneo, M. Florencia; Álvarez-Alvarado, José M.; Córdova-Esparza, Diana-Margarita; Chaparro-Sánchez, Ricardo; Terven, Juan; Rodríguez-Reséndiz, Juvenal

doi:10.3390/sym18091429

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection

by

Agosto de la Gala-Ureña

¹

,

Julio-Alejandro Romero-González

¹

,

M. Florencia Assaneo

²

,

José M. Álvarez-Alvarado

^3,*

,

Diana-Margarita Córdova-Esparza

¹

,

Ricardo Chaparro-Sánchez

¹

,

Juan Terven

⁴

and

Juvenal Rodríguez-Reséndiz

^3,*

¹

Facultad de Informática, Universidad Autónoma de Querétaro, Av. de las Ciencias S/N, Juriquilla, Santiago de Queretaro 76230, Mexico

²

Instituto de Neurobiología, Universidad Nacional Autónoma de México, Santiago de Queretaro 76230, Mexico

³

Facultad de Ingeniería, Universidad Autónoma de Querétaro, Santiago de Queretaro 76010, Mexico

⁴

Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada-Unidad Querétaro, Instituto Politécnico Nacional, Cerro Blanco 141, Colinas del Cimatario, Santiago de Queretaro 76090, Mexico

^*

Authors to whom correspondence should be addressed.

Symmetry 2026, 18(9), 1429; https://doi.org/10.3390/sym18091429

Submission received: 4 July 2026 / Revised: 16 August 2026 / Accepted: 24 August 2026 / Published: 26 August 2026

(This article belongs to the Special Issue Symmetry in Data Analysis and Optimization)

Download Versions Notes

Abstract

Street cries are vocal expressions used by hawkers to advertise products or services in public spaces. Although they may reflect adaptation to noisy urban environments, their acoustic characteristics remain poorly understood. This study evaluated whether street cries (SC) differ acoustically from the hawkers’ normal speaking voices (NV) and whether these differences can be captured using compact feature subsets. Sixteen acoustic features related to fundamental frequency, formant structure, spectral properties, and voice quality were extracted. Redundant features were removed based on Kendall’s

τ

correlations, after which four classifiers were evaluated: support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), and Gaussian naive Bayes (GNB). Binary particle swarm optimization (BPSO) was then used for feature selection, with

α

controlling the trade-off between cross-validated balanced accuracy and subset size. In repeated participant-grouped cross-validation, SVM achieved the highest mean balanced accuracy with the 13-feature vector (0.887 ± 0.056). On the held-out test set, BPSO-selected subsets yielded balanced accuracies of 0.783–0.900. The best SVM and GNB configurations both achieved 0.900 using six and four features, respectively. The features

f_{0}

and

F_{4}

appeared in all selected subsets. These results indicate that SC and NV can be differentiated using parsimonious, interpretable acoustic feature sets.

Keywords: street cries; acoustic characterization; feature selection; binary particle swarm optimization; uniform manifold approximation and projection; machine learning

Share and Cite

MDPI and ACS Style

Gala-Ureña, A.d.l.; Romero-González, J.-A.; Assaneo, M.F.; Álvarez-Alvarado, J.M.; Córdova-Esparza, D.-M.; Chaparro-Sánchez, R.; Terven, J.; Rodríguez-Reséndiz, J. Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection. Symmetry 2026, 18, 1429. https://doi.org/10.3390/sym18091429

AMA Style

Gala-Ureña Adl, Romero-González J-A, Assaneo MF, Álvarez-Alvarado JM, Córdova-Esparza D-M, Chaparro-Sánchez R, Terven J, Rodríguez-Reséndiz J. Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection. Symmetry. 2026; 18(9):1429. https://doi.org/10.3390/sym18091429

Chicago/Turabian Style

Gala-Ureña, Agosto de la, Julio-Alejandro Romero-González, M. Florencia Assaneo, José M. Álvarez-Alvarado, Diana-Margarita Córdova-Esparza, Ricardo Chaparro-Sánchez, Juan Terven, and Juvenal Rodríguez-Reséndiz. 2026. "Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection" Symmetry 18, no. 9: 1429. https://doi.org/10.3390/sym18091429

APA Style

Gala-Ureña, A. d. l., Romero-González, J.-A., Assaneo, M. F., Álvarez-Alvarado, J. M., Córdova-Esparza, D.-M., Chaparro-Sánchez, R., Terven, J., & Rodríguez-Reséndiz, J. (2026). Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection. Symmetry, 18(9), 1429. https://doi.org/10.3390/sym18091429

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Toward an Acoustic Characterization of Street Cries: A Machine Learning-Based Approach with Parsimonious Feature Selection

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI