Answers are grounded in this paper and cite their sources.
There is already a lot of research in the literature on the binary separation of healthy people and people with some illnesses that affects speech. However, there are only a few examinations where more illnesses are recognized together. The examination of the latter is justified by the fact that a person may suffer from several illnesses at the same time to a certain extent. In the present study, multiclass classification of depression, Parkinson's disease, and general voice disorders (organic and functional dysphonia) was performed using speech samples. Foremost, several acoustic features were examined as input (such as Mel-Frequency Cepstral Coefficients (MFCCs), mel-band energy values, formants and their bandwidths). Using the inputs, auto-and cross-correlation structures were formed as image representations and fed to a convolutional neural network (CNN). Parameter optimization of the correlation structures and the CNN model was applied to achieve the highest accuracy. Moreover, the result of the tuned process was compared to the result of a baseline process. Finally, multiclass (5 and 4 classes) classification was performed with the best parameters. The prominent feature set was the MFCCs (55.9% accuracy, for 5 class classification. 64.3% accuracy and 60.0% macro F1-score was obtained for 5 classes after parameter optimization. For classifying 4 classes (merging dysphonic ones together), 74.9% accuracy and 71.7% macro F1-score was achieved.
No takes yet. Share an insight, caveat, or question.
Jenei et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: