Abstract
In this paper a description of an algorithm purposed to a speech recognition problem is presented. Samples were obtained from people in different ages, from 8 to 70 years. Authors’ attention was concentrated on finding an efficient voice descriptor for the speech recognition process. To reach this goal Toeplitz matrices were used. The recognition process is based on k Nearest Neighbors algorithm and the analysis is carried out only for voiced parts of speech. Different distance metrics were compared in the aim of kNN optimization. In the research the influence of the sex recognition on final results is confirmed. The algorithm was tested for signals sampled with the rate of 8 kHz to keep all the necessary information contained in human voice.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abu Shariah, M.A.M., Ainon, R.N., Khalifa, O.O., Zainuddin, R.: Human Computer Interaction Using Isolated-Words Speech Recognition Technology. In: IEEE Proceedings of The International Conference on Intelligent and Advanced, pp. 1173–1178 (2007)
Amin, M.R., Bhotto, M.Z.: Bangali Text Dependent Speaker Identification Using Mel Frequency Cepstrum Coefficient and Vector Quantization. In: 3rd International Conference on Electrical and Computer Engineering, Dhaka Bangladesh, pp. 569–572 (2004)
Saeed, K., Szczepański, A.: A study on Noisy Speech Recognition. In: ICBAKE 2009 Proceedings of the 2009 International Conference on Biometrics and Kansei Engineering, Cieszyn Poland, pp. 142–147 (2009)
Titze, I.R.: Principles of voice production. Prentice Hall (1994)
Grey Jr., A.H., Wong, D.Y.: The Burg Algorithm for LPC Speech Analysis/Synthesis. IEEE Transactions on Acoustic, Speech and Signal Processing 28(6), 609–615 (1980)
Nammous, M.K., Saeed, K.: A Speech-and-Speaker Identification System: Feature Extraction, Description, and Classification of Speech-Signal Image. IEEE Transactions on Industrial Electronics 54(2), 887–897 (2007)
Saeed, K.: Image Analysis for Object Recognition. Bialystok Technical University Press, Białystkok (2004)
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Karwan, J., Saeed, K. (2011). A New Algorithm for Speech and Gender Recognition on the Basis of Voiced Parts of Speech. In: Chaki, N., Cortesi, A. (eds) Computer Information Systems – Analysis and Technologies. Communications in Computer and Information Science, vol 245. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27245-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-27245-5_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27244-8
Online ISBN: 978-3-642-27245-5
eBook Packages: Computer ScienceComputer Science (R0)