Limited receptive area neural classifier for recognition of swallowing sounds using short-time Fourier transform
Document Type
Conference Proceeding
Publication Date
12-1-2007
Abstract
In this paper we propose a sound recognition technique based on the limited receptive area (LIRA) neural classifier and short-time Fourier transform (STFT). LIRA neural classifier was developed as a multipurpose image recognition system. Previous tests of LIRA demonstrated good results in different image recognition tasks including: handwritten digit recognition, face recognition, metal surface texture recognition, and micro work piece shape recognition. We propose a sound recognition technique where spectrograms of sound instances serve as inputs of the LIRA neural classifier. The methodology was tested in recognition of swallowing sounds. Swallowing sound recognition may be employed in systems for automated swallowing assessment and diagnosis of swallowing disorders. The experimental results suggest high efficiency and reliability of the proposed approach. ©2007 IEEE.
Publication Title
IEEE International Conference on Neural Networks - Conference Proceedings
Recommended Citation
Makeyev, O.,
Sazonov, E.,
Schuckers, S.,
Melanson, E.,
&
Neuman, M.
(2007).
Limited receptive area neural classifier for recognition of swallowing sounds using short-time Fourier transform.
IEEE International Conference on Neural Networks - Conference Proceedings, 1601-1606.
http://doi.org/10.1109/IJCNN.2007.4371197
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/10631