Estimation of Hardware Requirements for Isolated Speech Recognition on an Embedded Systems

• Autorzy: Kłobucki K. , Mąka T.
• Języki publikacji: EN

Abstrakty

EN

In recent years, speech recognition functionality is increasingly being added in embedded devices. Because of limited resources in these devices, there is a need to assess whether the defined speech recognition system is feasible within given constraints, as well as estimating how many resources the system needs. In this paper, an attempt has been taken to define a technique for estimating hardware resources usage in the speech recognition task. To determine the parameters and their dependencies in this task, the two systems were tested. The first system utilized Dynamic Time Warping pattern matching technique, the second used Hidden Markov Models. For each case, the measurement of recognition rate and time, vocabulary database size and learning time has been performed. Obtained results have been exploited to define linear and polynomial regression models, and finally, an estimation algorithm has been developed using these models. After testing proposed approach, it was observed that even low-end mobile phones have sufficient hardware resources for realisation of isolated speech recognition system.

Słowa kluczowe

EN

isolated speech recognition; ASR; resources estimation

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2011
• Tom: Vol. 57, No. 4
• Strony: 483--488
• Opis fizyczny: Bibliogr. 11 poz., tab.

Twórcy

autor

Kłobucki K.

autor

Mąka T.

• Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Żołnierska 49, 71-210 Szczecin, Poland,

Bibliografia

• [1] Z.-H. Tan and B. Lindberg, Automatic Speech Recognition on Mobile Devices and over Communication Networks. Springer-Verlag, 2008, pp. 2–21.
• [2] L. Rabiner and W. Schafer, Theory and Applications of Digital Speech Processing. Prentice-Hall, 2010, pp. 950–984.
• [3] V. Amudha, B.Venkataramani, R. V. kumar, and S. Ravishankar, “Software/Hardware Co-Design of HMM Based Isolated Digit Recognition System,” Journal Of Computers, vol. 4, no. 3, pp. 154–159, 2009.
• [4] S. Grassi, M. Ansorge, F. Pellandini, and P.-A. Farine, “Implementation of Automatic Speech Recognition for Low-Power Miniaturized Devices,” in Proceedings of 5th COST 276 Workshop on Information and Knowledge Management for Integrated Media Communication, Prague, Czech Republic, 2–3 October 2003, pp. 59–64.
• [5] S. Jalali, Trends and Implications in Embedded Systems Development. TCS white paper, 2009.
• [6] C. Levy, G. Linares, and J.-F. Bonastre, “GMM-Based Acoustic Modeling for Embedded Speech Recognition,” in INTERSPEECH 2006 – ICSLP, Ninth International Conference on Spoken Language Processing, Pittsburgh, PA, USA, 17-21 September 2006.
• [7] A. Peinado and J. Segura, Speech Recognition Over Digital Channels: Robustness and Standards. John Wiley & Sons, Inc., 2006, pp. 8–77.
• [8] P. Senin, “Dynamic time warping algorithm review,” University of Hawaii at Manoa, Tech. Rep., 2008.
• [9] S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book Version 3.4. Cambridge University Press, 2006.
• [10] L. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition. Prentice Hall, 1993, pp. 219–226.
• [11] D. Larose, Data Mining Methods and Models. Wiley-IEEE Press, 2006, pp. 36–98.