Title | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/icassp.2019.8683099 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Sleep-disordered breathing, deep learning, hidden Markov model, bottleneck features, corpus | Mel-frequency cepstrum,Bottleneck,Autoencoder,Sound detection,Pattern recognition,Computer science,Artificial intelligence,Deep learning,Hidden Markov model,Hybrid system,Language model | Journal |
Volume | ISSN | Citations |
abs/1904.02992 | 1520-6149 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hector E. Romero | 1 | 0 | 0.34 |
Ning Ma | 2 | 21 | 2.66 |
Guy J. Brown | 3 | 31 | 3.38 |
Amy V. Beeston | 4 | 2 | 1.07 |
Madina Hasan | 5 | 13 | 5.35 |