Deep Learning Based Dysarthria Detection: A Comprehensive Approach

Making a model that can analyze numerous input features and predict whether a person will develop dysarthria is the first step in utilizing machine learning to forecast diseases like dysarthria. A motor speech disorder called dysarthria can be caused by a variety of underlying conditions, such as degenerative disorders, traumatic brain injuries, or neurological disorders. The authors used the 2000 audio signals from males and females with and without dysarthria from the TORGO data set. To extract the important features from the audio signals, the authors used the MFCC approach. To determine if dysarthria is present or absent, a machine learning model or algorithm will be fed with these MFCC coefficients.