Exploring Spectrogram-Based Audio Classification for Parkinson’s Disease: A Study on Speech Classification and Qualitative Reliability Verification
Sensors · 17.07.2024 · 24 (14) · 4625
DOI: 10.3390/s24144625 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.07.2024. Verfasst von Seung-Min Jeong und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of AI & Informatics, Graduate School, Sangmyung University, Hongjimun 2-gil 20, Jongno-gu, Seoul 03016, Republic of Korea. Hauptthemen laut MEDLINE: Parkinson Disease, Speech. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, NRF (National Research Foundation) of Korea.
Abstract (Originalsprache)
Patients suffering from Parkinson’s disease suffer from voice impairment. In this study, we introduce models to classify normal and Parkinson’s patients using their speech. We used an AST (audio spectrogram transformer), a transformer-based speech classification model that has recently outperformed CNN-based models in many fields, and a CNN-based PSLA (pretraining, sampling, labeling, and aggregation), a high-performance model in the existing speech classification field, for the study. This study compares and analyzes the models from both quantitative and qualitative perspectives. First, qualitatively, PSLA outperformed AST by more than 4% in accuracy, and the AUC was also higher, with 94.16% for AST and 97.43% for PSLA. Furthermore, we qualitatively evaluated the ability of the models to capture the acoustic features of Parkinson’s through various CAM (class activation map)-based XAI (eXplainable AI) models such as GradCAM and EigenCAM. Based on PSLA, we found that the model focuses well on the muffled frequency band of Parkinson’s speech, and the heatmap analysis of false positives and false negatives shows that the speech features are also visually represented when the model actually makes incorrect predictions. The contribution of this paper is that we not only found a suitable model for diagnosing Parkinson’s through speech using two different types of models but also validated the predictions of the model in practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of AI & Informatics, Graduate School, Sangmyung University, Hongjimun 2-gil 20, Jongno-gu, Seoul 03016, Republic of Korea.
- Department of Human-Centered Artificial Intelligence, Sangmyung University, Hongjimun 2-gil 20, Jongno-gu, Seoul 03016, Republic of Korea.
- Department of Neurology, Seoul National University College of Medicine, Seoul National University Hospital, Daehak-ro 101, Jongno-gu, Seoul 03080, Republic of Korea.
ORCID-Profile: Seung-Min Jeong, Seunghyun Kim, Eui Chul Lee, Han Joon Kim
Förderung
- National Research Foundation of Korea
- NRF (National Research Foundation) of Korea
Zitieren
APA
Jeong, S. M., Kim, S., Lee, E. C., & Kim, H. J. (2024). Exploring Spectrogram-Based Audio Classification for Parkinson’s Disease: A Study on Speech Classification and Qualitative Reliability Verification. Sensors, 24(14), 4625. https://doi.org/10.3390/s24144625
Vancouver
Jeong SM, Kim S, Lee EC, Kim HJ. Exploring Spectrogram-Based Audio Classification for Parkinson’s Disease: A Study on Speech Classification and Qualitative Reliability Verification. Sensors. 2024;24(14):4625. doi:10.3390/s24144625
BibTeX
@article{Jeong2024,
author = {Jeong, Seung-Min and Kim, Seunghyun and Lee, Eui Chul and Kim, Han Joon},
title = {Exploring Spectrogram-Based Audio Classification for Parkinson’s Disease: A Study on Speech Classification and Qualitative Reliability Verification},
journal = {Sensors},
year = {2024},
volume = {24},
number = {14},
pages = {4625},
doi = {10.3390/s24144625}
}
EUVIMED