Convolutional neural networks for pathological voice detection

Wu, Huiyi and Soraghan, John and Lowit, Anja and Di Caterina, Gaetano (2018) Convolutional neural networks for pathological voice detection. In: 40th International Conference of the IEEE Engineering in Medicine and Biology Society, 2018-07-17 - 2018-07-21.

[thumbnail of Wu-etal-EMBC-2018-Convolutional-neural-networks-for-pathological-voice]
Preview
Text. Filename: Wu_etal_EMBC_2018_Convolutional_neural_networks_for_pathological_voice.pdf
Accepted Author Manuscript

Download (707kB)| Preview

Abstract

Acoustic analysis using signal processing tools can be used to extract voice features to distinguish whether a voice is pathological or healthy. The proposed work uses spectrogram of voice recordings from a voice database as the input to a Convolutional Neural Network (CNN) for automatic feature extraction and classification of disordered and normal voice. The novel classifier achieved 88.5%, 66.2% and 77.0% accuracy on training, validation and testing data set respectively on 482 normal and 482 organic dysphonia speech files. It reveals that the proposed novel algorithm on the Saarbruecken Voice Database can effectively been used for screening pathological voice recordings.

ORCID iDs

Wu, Huiyi, Soraghan, John ORCID logoORCID: https://orcid.org/0000-0003-4418-7391, Lowit, Anja ORCID logoORCID: https://orcid.org/0000-0003-0842-584X and Di Caterina, Gaetano ORCID logoORCID: https://orcid.org/0000-0002-7256-0897;