Design and Implementation of Speech Recognition System Based on Field Programmable Gate Array

In this paper, a Hidden Markov Model (HMM) speech recognition system which is based on Field Programmable Gate Array (FPGA) is designed. It introduces the principle of speech recognition algorithm and deduces the hardware frameworks accordingly. In terms of HMM recognition module, the conventional Viterbi algorithm has been improved and recognition speed has been increased. The core part of the hardware is EP2S60F1020C3 FPGA chip. The experimental result of this system shows that the speech recognition accuracy reaches 94% when ten numbers are being recognized, and the average recognition time is 0.669s.

[1]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[2]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[3]  Jun-Dong Cho,et al.  Low power VLSI architecture of Viterbi scorer for HMM-based isolated word recognition , 2002, Proceedings International Symposium on Quality Electronic Design.

[4]  Eric A. Brewer,et al.  Hardware speech recognition for user interfaces in low cost, low power devices , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[5]  Steven F. Quigley,et al.  Implementing a simple continuous speech recognition system on an FPGA , 2002, Proceedings. 10th Annual IEEE Symposium on Field-Programmable Custom Computing Machines.

[6]  A. H. Khalil,et al.  A FPGA-based HMM for a discrete Arabic speech recognition system , 2003, Proceedings of the 12th IEEE International Conference on Fuzzy Systems (Cat. No.03CH37442).

[7]  Yoshikazu Miyanaga,et al.  A low-power VLSI design of an HMM based speech recognition system , 2002, The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002..