Correlation between Speech Quality and Weather
This paper deals with an impact of atmospheric conditions on the speech quality in the GSM. We found out a correlation between weather conditions and the speech quality. The GSM technology is the most widely utilized communication standard which it is now coming to its bandwidth limitation especially in big cities and densely populated areas. Under such circumstances, even a minor weather change and rain could be a decisive factor causing changes in the quality of service. We have obtained both meteorological data and Mean Opinion Score value specifying the current speech quality in the GSM network. Those data are evaluated and compiled via statistical methods, whose accomplishment is dataset competent to be utilized by more advanced data mining methods. According to space distribution and fragmentation, our team has chosen set of suitable methods used to find data-mining, data analysis and correlation. As a computation result, our team found out the correlation between current rain density and the speech quality. Results from the MOS tests are reported, and an analysis of the obtained speech samples is presented. Outcomes are summarized and potential further directions for the continuation of research are discussed.
KeywordsGSM Correlation Mean Opinion Score K-mean
Unable to display preview. Download preview PDF.
- 1.ITU-T: P.862: Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs (2001)Google Scholar
- 2.Rozhon, J., Voznak, M.: Development of a speech quality monitoring tool based on ITU-T P.862. In: Proceedings 34th International Conference on Telecommunications and Signal Processing, Budapest, Article number 6043771, pp. 62–66 (2011)Google Scholar
- 3.Fung, G.: A Comprehensive Overview of Basic Clustering Algorithms (2001)Google Scholar
- 4.Tomala, K., Macura, L., Voznak, M., Vychodil, J.: Monitoring the Quality of Speech in the Communication System BESIP. In: Proc. 35th International Conference on Telecommunication and Signal Processing, Prague, pp. 255–258 (2012)Google Scholar
- 5.ITU-T Recommendation G.107, The E-model: A computational model for use in transmission planning, Geneva (April 2009) Google Scholar
- 6.Voznak, M., Tomes, M., Vaclavikova, Z., Halas, M.: E-model Improvement for Speech Quality Evaluation Including Codecs Tandeming. In: Advances in Data Networks, Communications, Computers, Faro, pp. 119–124 (2010)Google Scholar
- 7.Opticom: Opticom quality testing products page, http://www.opticom.de/products/product-overview.php
- 8.Mouly, M., Pautet, M.-B.: The GSM System for Mobile Communications. Telecom Publishing (1992)Google Scholar
- 9.Saunders, S.R., Zavala, A.A.: Antennas and Propagation for Wireless Systems, 2nd edn. Wiley (2007)Google Scholar
- 11.Lee, S.D., Kao, B., Cheng, R.: Reducing UK-means to k-means. In: ICDM Workshops, pp. 483–488. IEEE Computer Society (2007)Google Scholar
- 12.Hongbo, S., Yaqin, L.: Naïve Bayes vs. Support Vector Machine: Resilience to Missing Data, Shanxi University of Finance and Economics 030031 Taiyuan, China, email@example.com, firstname.lastname@example.orgGoogle Scholar
- 14.Pengely, D., Cheng, C., Campbell, M.: Influence of Weather and Air Pollution on Mortality in Toronto, Toronto, Ontario (2005)Google Scholar