Speech and Sound Use in a Remote Monitoring System for Health Care
Ageing affects the economic and social foundations of societies at world level. Health care has to respond to the challenge that population ageing presents. Medical remote monitoring needs human operator to be assisted by means of smart information systems. Physiological and position sensors give numerous data, but speech analysis and sound classification can give interesting additional information about the patient and may help in decision-making. The entire analysis system is composed of parallel tasks: signal detection and channel selection, sound/speech classification, life sound classification and speech recognition. The multichannel sound processing allows us to localize the source of sound in the apartment and to select appropriate signal segments for analysis. Recognized key words indicative of a distress situation are extracted from sentences. Key words and classification results are sent to the medical remote monitoring application through network. An adapted speech corpus was recorded in French and used for evaluation purposes.
KeywordsHide Markov Model Speech Recognition Gaussian Mixture Model Gaussian Model Remote Monitoring
Unable to display preview. Download preview PDF.
- 1.European Commission: Europe’s response to World Ageing. Promoting economic and social progress in an ageing world. In: A contribution of the European Commission to the Second World Assembly on Ageing, March 18 (2002)Google Scholar
- 4.Real World Computing Partnership: CD – Sound Scene Database in Real Acoustical Environments (1998–2001)Google Scholar
- 5.Reynolds, D.: Speaker Identification and Verification using Gaussian Mixture Speaker Models. In: Workshop on Automatic Speaker Recognition, Identification and Verification, Martigny, Switzerland, pp. 27–30 (1994)Google Scholar
- 6.Pinquier, J., Senac, C., Andre-Obrecht, R.: Speech and music classification in audio documents. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 4, p. 4164 (2002)Google Scholar
- 8.Yamada, T., Watanabe, N.: Voice Activity Detection using non-Speech Models and HMM Composition. In: Workshop on Hands-free Speech Communication, Tokyo, Japan (2001)Google Scholar
- 9.Akbar, M., et al.: Parole et traduction automatique: le module de reconnaissance RAPHAEL. In: Proc. COLING-ACL 1998, Montréal, Quebec, vol. 2, pp. 36–40 (1998)Google Scholar
- 10.Vaufreydaz, D., et al.: Internet Documents—a Rich Source for Spoken Language Modeling. In: Proc. IEEE Workshop ASRU 1999, Keystone-Colorado, USA, pp. 277–281 (1999)Google Scholar
- 11.Gauvain, J.L., Lamel, L.F., Eskenazi, M.: Design considerations and text selection for BREF, a large French read-speech corpus. In: Proc. ICSLP 1990, Kobe, Japan, pp. 1097–1100 (1990)Google Scholar
- 12.Vaufreydaz, D., et al.: A New Methodology for Speech Corpora Definition from Internet Documents. In: Proc. LREC 2000, 2nd Int. Conf. on Language Resources and Evaluation, Athens, Greece, pp. 423–426 (2000)Google Scholar