Deep Neural Network for Automatic Assessment of Dysphonia
This work addresses the need for objective and consistent vocal quality assessment in medical or speech therapy contexts, though it is incremental as it applies existing deep learning methods to a specific domain.
The paper tackled the problem of automatically assessing dysphonia severity on the GRBAS scale using a deep neural network, achieving performance close to human intra-rater levels and exceeding inter-rater performance in terms of precision and mean absolute error.
The purpose of this work is to contribute to the understanding and improvement of deep neural networks in the field of vocal quality. A neural network that predicts the perceptual assessment of overall severity of dysphonia in GRBAS scale is obtained. The design focuses on amplitude perturbations, frequency perturbations, and noise. Results are compared with performance of human raters on the same data. Both the precision and the mean absolute error of the neural network are close to human intra-rater performance, exceeding inter-rater performance.