Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing

Abstract: 

Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification of SDB sounds, such as snoring, using bottleneck features learned from a corpus of whole-night sound recordings. Two types of bottleneck features are described, obtained by applying a deep autoencoder to the output of an auditory model or a short-term autocorrelation analysis. We investigate two architectures for snore sound detection: a tandem system and a hybrid system. In both cases, a ‘language model’ (LM) was incorporated to exploit information about the sequence of different SDB events. Our results show that the proposed bottleneck features give better performance than conventional mel-frequency cepstral coefficients, and that the tandem system outperforms the hybrid system given the limited amount of labelled training data available. The LM made a small improvement to the performance of both classifiers.

https://ieeexplore.ieee.org/document/8683099

up
0 users have voted:

Paper Details

Authors:
Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan
Submitted On:
8 May 2019 - 9:03am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Hector E. Romero
Document Year:
2019
Cite

Document Files

poster

(61)

Subscribe

[1] Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan, "Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4089. Accessed: Dec. 06, 2019.
@article{4089-19,
url = {http://sigport.org/4089},
author = {Hector E. Romero; Ning Ma; Guy J. Brown; Amy V. Beeston; Madina Hasan },
publisher = {IEEE SigPort},
title = {Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing},
year = {2019} }
TY - EJOUR
T1 - Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing
AU - Hector E. Romero; Ning Ma; Guy J. Brown; Amy V. Beeston; Madina Hasan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4089
ER -
Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan. (2019). Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing. IEEE SigPort. http://sigport.org/4089
Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan, 2019. Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing. Available at: http://sigport.org/4089.
Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan. (2019). "Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing." Web.
1. Hector E. Romero, Ning Ma, Guy J. Brown, Amy V. Beeston, Madina Hasan. Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4089