Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection

We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

[1]  P. Lloberes,et al.  Self-reported sleepiness while driving as a risk factor for traffic accidents in patients with obstructive sleep apnoea syndrome and in non-apnoeic snorers. , 2000, Respiratory medicine.

[2]  Pedro Gómez Vilda,et al.  Dimensionality Reduction of a Pathological Voice Quality Assessment System Based on Gaussian Mixture Models and Short-Term Cepstral Parameters , 2006, IEEE Transactions on Biomedical Engineering.

[3]  Mireia Farrús,et al.  Using jitter and shimmer in speaker verification , 2009 .

[4]  Germán Castellanos-Domínguez,et al.  Automatic Detection of Pathological Voices Using Complexity Measures, Noise Parameters, and Mel-Cepstral Coefficients , 2011, IEEE Transactions on Biomedical Engineering.

[5]  Luis A. Hernández Gómez,et al.  Design of a Multimodal Database for Research on Automatic Detection of Severe Apnoea Cases , 2008, LREC.

[6]  M. Robb,et al.  Vocal tract resonance characteristics of adults with obstructive sleep apnea. , 1997, Acta oto-laryngologica.

[7]  P. Monoson,et al.  Speech dysfunction of obstructive sleep apnea. A discriminant analysis of its descriptors. , 1989, Chest.

[8]  José B. Mariño,et al.  Albayzin speech database: design of the phonetic corpus , 1993, EUROSPEECH.

[9]  Eduardo López,et al.  Analyzing Training Dependencies and Posterior Fusion in Discriminant Classification of Apnea Patients Based on Sustained and Connected Speech , 2011, INTERSPEECH.

[10]  Donald G. Childers,et al.  Speech processing and synthesis toolboxes , 1999 .

[11]  R. Jané,et al.  Acoustic analysis of vowel emission in obstructive sleep apnea. , 1993, Chest.

[12]  A. Murray,et al.  Systematic comparison of different algorithms for apnoea detection based on electrocardiogram recordings , 2002, Medical and Biological Engineering and Computing.

[13]  Donald G. Childers,et al.  Speech Processing , 1999 .

[14]  Federica Provini,et al.  Cardiovascular Disorders and Obstructive Sleep Apnea Syndrome , 2006, Clinical and experimental hypertension.

[15]  Chafic Mokbel,et al.  BECARS: a free software for speaker verification , 2004, Odyssey.

[16]  Luis A. Hernández Gómez,et al.  Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques , 2009, EURASIP J. Adv. Signal Process..

[17]  Max A. Little,et al.  Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity , 2011, Journal of The Royal Society Interface.