Simultaneous Speech and Eating Behavior Recognition Using Data Augmentation and Two-Stage Fine-Tuning
Sensors · 02.03.2025 · 25 (5) · 1544
DOI: 10.3390/s25051544 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.03.2025. Verfasst von Toshihiro Tsukagoshi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Science and Technology, Shizuoka University, 3-5-1 Johoku, Chuo-ku, Hamamatsu 432-8011, Japan. Hauptthemen laut MEDLINE: Feeding Behavior, Speech. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: New Energy and Industrial Technology Development Organization, Japan Society for the Promotion of Science, Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research.
Abstract (Originalsprache)
Speaking and eating are essential components of health management. To enable the daily monitoring of these behaviors, systems capable of simultaneously recognizing speech and eating behaviors are required. However, due to the distinct acoustic and contextual characteristics of these two domains, achieving high-precision integrated recognition remains underexplored. In this study, we propose a method that combines data augmentation through synthetic data creation with a two-stage fine-tuning approach tailored to the complexity of domain adaptation. By concatenating speech and eating sounds of varying lengths and sequences, we generated training data that mimic real-world environments where speech and eating behaviors co-exist. Additionally, efficient model adaptation was achieved through two-stage fine-tuning of the self-supervised learning model. The experimental evaluations demonstrate that the proposed method maintains speech recognition accuracy while achieving high detection performance for eating behaviors, with an F1 score of 0.918 for chewing detection and 0.926 for swallowing detection. These results underscore the potential of using voice recognition technology for daily health monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Science and Technology, Shizuoka University, 3-5-1 Johoku, Chuo-ku, Hamamatsu 432-8011, Japan.
- Department of Smart Design, Faculty of Architecture and Design, Aichi Sangyo University, 12-5 Harayama, Oka-cho, Okazaki 444-0005, Japan.
ORCID-Profile: Masafumi Nishimura
Förderung
- New Energy and Industrial Technology Development Organization
- Japan Society for the Promotion of Science
- Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research
Zitieren
APA
Tsukagoshi, T., Nishida, M., & Nishimura, M. (2025). Simultaneous Speech and Eating Behavior Recognition Using Data Augmentation and Two-Stage Fine-Tuning. Sensors, 25(5), 1544. https://doi.org/10.3390/s25051544
Vancouver
Tsukagoshi T, Nishida M, Nishimura M. Simultaneous Speech and Eating Behavior Recognition Using Data Augmentation and Two-Stage Fine-Tuning. Sensors. 2025;25(5):1544. doi:10.3390/s25051544
BibTeX
@article{Tsukagoshi2025,
author = {Tsukagoshi, Toshihiro and Nishida, Masafumi and Nishimura, Masafumi},
title = {Simultaneous Speech and Eating Behavior Recognition Using Data Augmentation and Two-Stage Fine-Tuning},
journal = {Sensors},
year = {2025},
volume = {25},
number = {5},
pages = {1544},
doi = {10.3390/s25051544}
}
EUVIMED