Enhancing SELD Performance: The Role of Data Augmentation Techniques in Spatial Sound Analysis
Sensors · 31.05.2026 · 26 (11) · 3466
DOI: 10.3390/s26113466 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 31.05.2026. Verfasst von Christian Santamaria und 5 weiteren Autor:innen. Beteiligte Einrichtung: Colegio de Ciencias e Ingenierías "El Politécnico", Universidad San Francisco de Quito USFQ, Diego de Robles S/N, Quito 170157, Ecuador. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad San Francisco de Quito, Universidad de Las Américas.
Abstract (Originalsprache)
Sound Event Localization and Detection (SELD) integrates Sound Event Detection (SED) and Direction-of-Arrival Estimation (DOAE) to recognize and localize sound events in various applications, including urban sound sensing, wildlife monitoring, and home surveillance. Recently, advancements in machine learning, particularly deep learning techniques, have demonstrated remarkable success in improving SELD performance. However, training deep learning models for SELD is challenged by the limited availability of high-quality spatial audio data, which is essential for accurate model generalization. This paper explores the effectiveness of data augmentation techniques in overcoming this limitation. We evaluate the impact of Frequency Shift (FS), Random Cutout (RC), and Channel Swapping (CS) on SELD performance using a comprehensive set of experiments. Our findings indicate that all tested augmentation combinations except FS alone significantly improve SELD performance, reducing the SELD error by approximately 8% compared to no augmentation. The differences among effective combinations are not statistically significant, suggesting that the decision to augment is more impactful than the specific combination chosen. This work highlights the critical role of data augmentation in enhancing SELD systems and suggests future research directions, including testing these techniques with different model architectures and exploring additional augmentation methods.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Colegio de Ciencias e Ingenierías "El Politécnico", Universidad San Francisco de Quito USFQ, Diego de Robles S/N, Quito 170157, Ecuador.
- Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
- Faculty of Engineering and Applied Sciences, Networking and Telecommunications Engineering, ETEL Research Group, Universidad de Las Américas (UDLA), Quito 170503, Ecuador.
ORCID-Profile: Felipe Grijalva, Henry Carvajal Mora
Förderung
- Universidad San Francisco de Quito
- Universidad de Las Américas
Zitieren
APA
Santamaria, C., Grijalva, F., Rosero, K., Vega-Sánchez, J., Garzón, N. O., & Mora, H. C. (2026). Enhancing SELD Performance: The Role of Data Augmentation Techniques in Spatial Sound Analysis. Sensors, 26(11), 3466. https://doi.org/10.3390/s26113466
Vancouver
Santamaria C, Grijalva F, Rosero K, Vega-Sánchez J, Garzón NO, Mora HC. Enhancing SELD Performance: The Role of Data Augmentation Techniques in Spatial Sound Analysis. Sensors. 2026;26(11):3466. doi:10.3390/s26113466
BibTeX
@article{Santamaria2026,
author = {Santamaria, Christian and Grijalva, Felipe and Rosero, Karen and Vega-Sánchez, José and Garzón, Nathaly Orozco and Mora, Henry Carvajal},
title = {Enhancing SELD Performance: The Role of Data Augmentation Techniques in Spatial Sound Analysis},
journal = {Sensors},
year = {2026},
volume = {26},
number = {11},
pages = {3466},
doi = {10.3390/s26113466}
}
EUVIMED