Title :
Classification of Audio Signals in All-Night Sleep Studies
Author :
Liao, Wen-Hung ; Su, Yi-Syuan
Author_Institution :
Dept. of Comput. Sci., National Cheng Chi Univ., Taipei
Abstract :
In this paper, we describe the classification of audio signals recorded in all-night sleep studies. Our objective is to separate the episodes into snoring sounds and non-snoring sounds. To begin with, we employ hierarchical classification schemes to classify sounds into human sounds and non-human sounds. We then attempt to organize human sounds into snore and non-snore segments based on their acoustic properties. We perform further analysis of the extracted snoring sounds to check if the testee has apnea. Experimental results have validated the efficacy of the proposed method
Keywords :
acoustic signal processing; audio signal processing; bioacoustics; medical signal processing; signal classification; sleep; all-night sleep studies; audio signal classification; obstructive sleep apnea; snoring sounds; sound classification; Acoustic testing; Computer science; Frequency; Hospitals; Humans; Noise reduction; Performance analysis; Performance evaluation; Sleep apnea; Speech;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.367