![](bg7.png)
of automatic diagnosis of OSA disease.. Preliminary
experimental results on the speech database
collected using state-of-the-art GMM speaker
recognition techniques shows that it is worth
continuing the research on this area. Related to
nasality factor as an important feature in the acoustic
characteristics of apnoea speakers, GMM approach
have confirmed that there are significant differences
between apnoea and control group on the relative
nasalization degree between different linguistic
contexts. Therefore, future research will be focused
on exploiting this information in order to use it for
the automatic apnoea diagnosis. Furthermore, best
results can be expected with a representation of the
audio data optimized for pathology discrimination
On the other hand, and bearing in mind the
speech database design criteria, we propose the use
of other acoustic measures usually applied over
pathological voices (jitter, HNR, etc.). These
techniques could also be applied over different
linguistic and phonetic contexts, and could be fussed
to GMM approach to improve our initial
discrimination results.
ACKNOWLEDGEMENTS
The activities described in this paper were funded by
the Spanish Ministry of Science and Technology as
part of the TEC2006-13170-C02-01 project. The
authors would like to thank the volunteers at
Hospital Clínico Universitario of Málaga, Spain, and
to Guillermo Portillo who made the speech and
image data collection possible.
REFERENCES
Blouet, R., Mokbel, C., Mokbel, H., Sanchez Soto, E.,
Chollet, G., & Greige, H. (2004). BECARS: a Free
Software for Speaker Verification. In Proceedings of
The Speaker and Language Recognition Workshop,
ODYSSEY, pp 145-148.
Coccagna, G., Pollini, A., & Provini, F. (2006).
Cardiovascular disorders and obstructive sleep apnea
syndrome. In Clinical and Experimental Hypertension
Vol. 28:217–24.
Do, M. N., (2003) Fast approximation of Kullback-Leibler
distance for dependence trees and Hidden Markov
Models. IEEE Signal Processing Letter 10, 115-118.
Fernandez R., Hernández L. A., López E., Alcázar J.,
Portillo G., & Toledano D. T. (2008). Design of a
Multimodal Database for Research on Automatic
Detection of Severe Apnoea Cases. In Proceedings of
6th Language Resources and Evaluation Conference.
LREC, Marrakech.
Fiz, J.A., Morera, J., Abad, J., Belsulnces, A., Haro, M.,
Fiz, J.I., Jane, R., Caminal, P., & Rodenstein, D.
(1993). Acoustic analysis of vowel emission in
obstructive sleep apnea. In Chest Journal; 104: 1093 –
1096.
Fox, A.W., & Monoson, P.K. (1993). Speech dysfunction
of obstructive sleep apnea. A discriminant analysis of
its descriptors. In Chest Journal; 96(3): 589-595.
Fredouille, C., Pouchoulin, G., Bonastre, J.F., Azzarello,
M., Giovanni, A., & Guio, A. (2005). Application of
Automatic Speaker Recognition techniques to
pathological voice assessment (dysphonia). In
Proceeding of 9th European Conference on Speech
Communication and Technology, Interspeech 2005,
Lisboa, p. 149-152.
Glass, J. , & Zue, V. (1985). Detection of nasalized
vowels in American English. In Proceedings of
Acoustics, Speech, and Signal Processing, IEEE
International Conference on ICASSP, Volume: 10, p.
1569- 1572.
Hidalgo, A., & Quilis, M. (2002). Fonética y fonología
españolas. Editorial Tirant blanch.
Lloberes, P., Levy, G., Descals, C., et al. (2000). Self-
reported sleepiness while driving as a risk factor for
traffic accidents in patients with obstructive sleep
apnoea syndrome and in non-apnoeic snorers. In
Respiratory Medicine 94: 971–6.
Moreno, A., Poch, D., Bonafonte, A., Lleida, E., Llisterri,
J., Mariño, J.B., & Naude, C. (1993). ALBAYZIN
Speech Database: Design of the Phonetic Corpus. In
Proceedings of Eurospecch 93. Berlin, Germany, 21-
23. Vol. 1 pp. 175-178.
Parsa, V., & Jamieson, D. G. (2001). Acoustic
discrimination of pathological voice : Sustained
vowels versus continuous speech. In Journal of
Speech, Language, and Hearing Research ISSN 1092-
4388, vol. 44, no2, pp. 327-339 (1 p.1/4).
Pruthi T. (2007) Analysis, vocal-tract modeling and
automatic detection of vowel nasalization. Doctor
Thesis at the University of Maryland.
Puertas, F.J., Pin, G., María, J.M., & Durán, J. (2005).
Documento de consenso Nacional sobre el síndrome
de Apneas-hipopneas del sueño (SAHS). Grupo
Español De Sueño (GES).
Reynolds, D.A., Quatieri, T.F., & Dunn, R.B. (2000).
Speaker verification using adapted gaussian mixture
models. In Digital Signal Processing 10: 19-41.
BIOSIGNALS 2009 - International Conference on Bio-inspired Systems and Signal Processing
130