Recognition of the numbers in the Polish language

• Autorzy: Plichta A. , Gąciarz T. , Krzywdziński T.
• Języki publikacji: EN

Abstrakty

EN

Automatic Speech Recognition is one of the hottest research and application problems in today’s ICT technologies. Huge progress in the development of the intelligent mobile systems needs an implementation of the new services, where users can communicate with devices by sending audio commands. Those systems must be additionally integrated with the highly distributed infrastructures such as computational and mobile clouds, Wireless Sensor Networks (WSNs), and many others. This paper presents the recent research results for the recognition of the separate words and words in short contexts (limited to the numbers) articulated in the Polish language. Compressed Sensing Theory (CST) is applied for the first time as a methodology of speech recognition. The effectiveness of the proposed methodology is justified in numerical tests for both separate words and short sentences.

Słowa kluczowe

EN

Automatic Speech Recognition; compressed sensing; Sparse Classification

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2013
• Tom: nr 4
• Strony: 70--78
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Plichta A.

• Institute of Computer Science, Tadeusz Kościuszko Cracow University of Technology, Cracow, Poland

autor

Gąciarz T.

• Institute of Computer Science, Tadeusz Kościuszko Cracow University of Technology, Cracow, Poland

autor

Krzywdziński T.

• Comarch SA, Cracow, Poland

Bibliografia

• [1] A. M. Peinado and J. C. Segura, Speech Recognition over Digital Channels. Robustness and Standards. Chichester, England: Wiley, 2006.
• [2] D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Lin- guistics, and Speech Recognition. New Jersey: Pearson Education, 2009.
• [3] L. Rabiner and B.-H. Juang, Fundamentals of speech recognition. New Jersey: AT&T, 1993.
• [4] P. Walendowski, An Application of SVM Artificial Neural Networks in Speech Recognition. Wrocław: Politechnika Wrocławska, 2008 (in Polish).
• [5] B. Plannerer, “An introduction to speech recognition”, tutorial, Uni- versity of Munich, Germany [Online]. Available: http://www.speech-recognition.de/ 2008.
• [6] W. Kasprzak, “Image and speech recognition”, E-lecture notes, Warsaw University of Technology, 2011, updated version 2012 [Online]. Available: www.ia.pw.edu.pl/_wkasprza/PAP/EIASR 2012.pdf
• [7] R. G. Bachu, S. Kopparthi, B. Adapa and B. D. Barkana, “Separation of voiced and unvoiced using zero crossing rate and energy of the speech signal”, American Society for Engineering Education (ASEE), Zone Conference Proceedings, 2008, pp. 1–7.
• [8] S. Boyd and L. Vandenberghe, Convex Optimization. Cambridge University Press, 2004.
• [9] J. F. Gemmeke and B. Cranen,“Using sparse representations for missing data imputation in noise robust speech recognition”, in Proc. 17th Eur. Sig. Proces. Conf. EUSIPCO 2009, Glasgow, Scotland, 2009, pp. 1755–1759.
• [10] J. Szabatin, Theory of the sygnals, Warszawa: Wydawnictwa Komunikacji i Łączności, 1982 (in Polish).
• [11] T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations”, in Proc. 10th Int. Conf. Speech & Comp. SPECOM 2005, Patras, Greece, 2005, pp. 191–194.
• [12] J.-L. Starck, F. Murtagh, and J. M. Fadili, Sparse Image and Signal Processing: Wavelets, Curvelets, Morphological Diversity. Cambridge University Press, 2010.
• [13] D. Needeel, “Topics in compressed sensing”, Ph.D. thesis, University of California, Davis, 2009.
• [14] N. Vaswani and W. Lu , “Modifed-CS: Modifying compressive sensing for problems with partially known support”, IEEE Trans. Sig. Proces., vol. 58, no. 9, pp. 4595–4607, 2010.
• [15] E. Candes,“The restricted isometry property and its implications for compressed sensing”, Compte Rendus de l’Academie des Sciences, vol. 346, no. 9–10, pp. 589–592, 2008.
• [16] J. F. Gemmeke and B. Cranen, “Noise robust digit recognition using sparse representations”, in Proc. ISCA Tutor. Res. Worksh. Speech Anal. Proces. Knowl. Discov., Aalborg, Denmark, 2008, pp. 1–4.
• [17] J. F. Gemmeke, “Classification on incomplete data using sparse representations: Imputation is optional”, in Proc. Benelearn 2008, Spa, Belgium, 2008, pp. 71–72.
• [18] J. Wright et al., “Robust face recognition via sparse representation”, IEEE Trans. Patt. Anal. Mach. Intell., vol. 31, no. 2, pp. 210–227, 2009.
• [19] D. Salomon, Data Compression: The Complete Reference. Springer, 2007.
• [20] N. Bhatia and Vandana,“Survey of nearest neighbor techniques”, Int. J. Comp. Sci. Inform. Secur., vol. 8, no. 2, pp. 302–305, 2010.