Automatic Wheezing Detection Using Speech Recognition Technique
Tóm tắt
This study developed a speech recognition technique to detect wheezing. Wheezes are important in the diagnosis of pulmonary pathologies such as asthma. The acoustic features of wheezes are distinct in the frequency domain. Therefore, many studies have focused on detecting wheezing peaks in spectrograms through image processing. However, automated detection of wheezing peaks is difficult because of blurred edges and noise. This paper proposes an alternative approach for wheezing detection in which the mel frequency cepstral coefficients (MFCCs) are integrated into the Gaussian mixture model (GMM). The MFCCs reduce the short-term spectral information to a few coefficients, and the GMM recognizes the respiratory sounds. The respiratory sounds of 18 volunteers (9 asthmatic and 9 normal adults) were recorded for training and testing. The results of a qualitative analysis of wheeze recognition showed a good sensitivity of 0.881 and a high specificity of 0.995.
Tài liệu tham khảo
citation_journal_title=European Respiratory Review; citation_title=Standardization of computerized respiratory sound analysis; citation_author=ARA Sovijarvi, J Vanderschoot, JE Earis; citation_volume=10; citation_publication_date=2000; citation_pages=585-649; citation_id=CR1
citation_journal_title=European Respiratory Review; citation_title=Characteristics of breath sounds and adventitious respiratory sounds; citation_author=ARA Sovijarvi, LP Malmberg, G Charbonneau, J Vanderschoot, F Dalmasso, C Sacco, M Rossi, JE Earis; citation_volume=10; citation_publication_date=2000; citation_pages=591-596; citation_id=CR2
citation_journal_title=Clinical Investigations, Clinical Investigations; citation_title=Analysis of forced wheezes in asthma patients; citation_author=JA Fiz, R Jane, J Izquierdo, A Homs, MA Garcia, R Gomez, E Monso, J Morera; citation_volume=73; citation_publication_date=2005; citation_pages=55-60; citation_id=CR3
citation_journal_title=Journal of Applied Physiology; citation_title=Spectral content of forced expiratory wheezes during air, He, and SF6 breathing in normal humans; citation_author=Y Shabtai-Musih, JB Grotberg, N Gavriely; citation_volume=72; citation_publication_date=1992; citation_pages=629-635; citation_id=CR4
citation_journal_title=IEEE Transaction on Biomedical Engineering; citation_title=Automated spectral characterization of wheezing in asthmatic children; citation_author=TR Fenton, H Pasterkamp, A Tal, V Chernick; citation_volume=32; citation_issue=1; citation_publication_date=1985; citation_pages=50-55; citation_doi=10.1109/TBME.1985.325616; citation_id=CR5
citation_journal_title=Technology and Health; citation_title=A new method for automatic wheeze detection; citation_author=M Waris, P Helisto, Saarinen Haltsonen, A Saarinen, AR Sovijarvi; citation_volume=6; citation_publication_date=1998; citation_pages=33-40; citation_id=CR6
citation_journal_title=IEEE Transaction on Biomedical Engineering; citation_title=Time-frequency detection and analysis of wheezes during forced exhalation; citation_author=A Homs-Corbera, JA Fiz, A Morera, R Jane; citation_volume=51; citation_publication_date=2004; citation_pages=182-186; citation_doi=10.1109/TBME.2003.820359; citation_id=CR7
citation_journal_title=Biomedical Engineering Applications, Basis & Communications; citation_title=Wheeze recognition based on 2D bilateral filtering of spectrogram; citation_author=BS Lin, BS Lin, HD Wu, FC Chong, SJ Chen; citation_volume=18; citation_publication_date=2006; citation_pages=128-137; citation_doi=10.4015/S1016237206000221; citation_id=CR8
citation_journal_title=IEEE Transactions on Biomedical Engineering; citation_title=Analysis of wheezes using wavelet higher order spectral features; citation_author=SA Taplidou, LJ Hadjileontiadis; citation_volume=57; citation_issue=7; citation_publication_date=2010; citation_pages=1596-1610; citation_doi=10.1109/TBME.2010.2041777; citation_id=CR9
citation_journal_title=IEEE Transactions on Biomedical Engineering; citation_title=Adventitious sounds identification and extraction using temporal–spectral dominance-based features; citation_author=F Jin, S Krishnan, F Sattar; citation_volume=58; citation_issue=11; citation_publication_date=2011; citation_pages=1596-1610; citation_id=CR10
citation_journal_title=International Journal of Applied Information Systems; citation_title=Detection and classification of abnormal respiratory sounds on a resource-constraint mobile device; citation_author=C Uwaoma, G Mansingh; citation_volume=7; citation_issue=11; citation_publication_date=2014; citation_pages=35-40; citation_doi=10.5120/ijais14-451265; citation_id=CR11
citation_journal_title=IEEE Sensors Journal; citation_title=Personal lung function monitoring devices; citation_author=AM Kwan, AG Fung, PA Jansen, M Schivo, NJ Kenyon, JP Delplanque, CE Davis; citation_volume=15; citation_issue=4; citation_publication_date=2015; citation_pages=2238-2247; citation_doi=10.1109/JSEN.2014.2373134; citation_id=CR12
citation_journal_title=Computers in Biology and Medicine; citation_title=Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes; citation_author=M Bahoura; citation_volume=39; citation_publication_date=2009; citation_pages=824-843; citation_doi=10.1016/j.compbiomed.2009.06.011; citation_id=CR13
citation_journal_title=International Journal of Engineering and Computer Science; citation_title=Acoustic analysis of voice samples to differentiate healthy and asthmatic persons; citation_author=K Batra, S Bhasin, A Singh; citation_volume=4; citation_issue=7; citation_publication_date=2012; citation_pages=13161-13164; citation_id=CR14
citation_journal_title=IEEE Transactions on Speech and Audio Processing; citation_title=Robust text-independent speaker identification using Gaussian mixture speaker models; citation_author=DA Reynolds, RC Rose; citation_volume=3; citation_issue=1; citation_publication_date=1995; citation_pages=72-82; citation_doi=10.1109/89.365379; citation_id=CR15
citation_journal_title=IEEE Transactions on Speech and Audio Processing; citation_title=Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition; citation_author=R Vergin, D O’Shaughnessy, A Farhat; citation_volume=7; citation_issue=5; citation_publication_date=1999; citation_pages=525-532; citation_doi=10.1109/89.784104; citation_id=CR16
citation_journal_title=IEEE Transactions on Neural Systems and Rehabilitation Engineering; citation_title=Experiments with fast Fourier transform, linear predictive and cepstral coefficients in dysarthric speech recognition algorithms using hidden Markov model; citation_author=PD Polur, GE Miller; citation_volume=13; citation_issue=4; citation_publication_date=2005; citation_pages=558-561; citation_doi=10.1109/TNSRE.2005.856074; citation_id=CR17
citation_journal_title=IEEE Transactions on Audio, Speech and Language Processing; citation_title=An effective algorithm for automatic detection and exact demarcation of breath sounds in speech and song signals; citation_author=D Ruinskiy, Y Lavner; citation_volume=15; citation_issue=3; citation_publication_date=2007; citation_pages=838-850; citation_doi=10.1109/TASL.2006.889750; citation_id=CR18
citation_journal_title=IEEE Transactions on Audio, Speech and Language Processing; citation_title=Speech analysis in a model of the central auditory system; citation_author=J Woojay, BH Juang; citation_volume=15; citation_issue=6; citation_publication_date=2007; citation_pages=1802-1817; citation_doi=10.1109/TASL.2007.900102; citation_id=CR19
citation_journal_title=Journal of Medical and Biological Engineering; citation_title=Tracheal opening discrimination during intubation using acoustic features and Gaussian mixture model; citation_author=WH Chen, YH Chiu, HC Wang, YW Hung, HP Su, KS Cheng; citation_volume=34; citation_issue=6; citation_publication_date=2014; citation_pages=605-611; citation_id=CR20
citation_journal_title=IEEE Transaction on Biomedical Engineering; citation_title=A model of acoustic transmission in the respiratory system; citation_author=GR Wodicka, KN Stevens, HL Golub, EG Cravalho, DC Shannon; citation_volume=36; citation_issue=9; citation_publication_date=1989; citation_pages=925-934; citation_doi=10.1109/10.35301; citation_id=CR21
citation_journal_title=Journal of the Acoustical Society of America; citation_title=A scale for the measurement of the psychological magnitude pitch; citation_author=SS Stevens, J Volkman; citation_volume=8; citation_publication_date=1937; citation_pages=185-190; citation_doi=10.1121/1.1915893; citation_id=CR22
citation_journal_title=Journal of the Royal Statistical Society: Series B; citation_title=Maximum likelihood from incomplete data via the EM algorithm; citation_author=AP Dempster, NM Laird, DB Rubin; citation_volume=39; citation_publication_date=1977; citation_pages=1-38; citation_id=CR23