Clustering pathologic voice with kohonen SOM and hierarchical clustering

Teixeira, João Paulo; Dajer, Maria; Oliveira, Alessa Anjos de

http://hdl.handle.net/10198/24674

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Artigo_Publicado.pdf		600.43 KB	Adobe PDF	Download

Send Feedback

Authors

Teixeira, João Paulo

Dajer, Maria

Oliveira, Alessa Anjos de

Abstract(s)

The main purpose of clustering voice pathologies is the attempt to form large groups of subjects with similar pathologies to be used with Deep-Learning. This paper focuses on applying Kohonen's Self-Organizing Maps and Hierarchical Clustering to investigate how these methods behave in the clustering procedure of voice samples by means of the parameters absolute jitter, relative jitter, absolute shimmer, relative shimmer, HNR, NHR and Autocorrelation. For this, a comparison is made between the speech samples of the Control group of subjects, the Hyper-functional Dysphonia and Vocal Folds Paralysis pathologies groups of subjects. As a result, the dataset was divided in two clusters, with no distinction between the pre-defined groups of pathologies. The result is aligned with previous result using statistical analysis.

Keywords

Acoustic parameters Clustering Hierarchical clustering Kohonen's self-organizing maps Unsupervised artificial neural networks Voice pathologies

URI

http://hdl.handle.net/10198/24674

Citation

Teixeira, João Paulo; Dajer, Maria; Oliveira, Alessa de (2021). Clustering pathologic voice with kohonen SOM and hierarchical clustering. In 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC), 14th Int Conf on Bio-inspired Systems and Signal Processing (BIOSIGNALS), 14th Int Conf on Biomedical Electronics and Devices (BIODEVICES). p. 158-163. ISBN 978-989-758-490-9