An ASIC-Based Artificial Neural Network Applied Real-time Speech Recognition SOPC
Abstract
Artificial Neural Network (ANN) is promoted to one of major schemes applied in pattern recognition area. Indeed, many approaches to software-based platforms have proven great performance of ANN. However, developing pattern recognition systems integrating ANN hardware-based architecture has been limited not only by the silicon requirements such as frequency, area, power, or resource but also by high accuracy and real-time applications strictly. Although a considerable number of ANN hardware-based architectures have been proposed currently, they have experienced a deprivation of functions due to both small configurations and ability of reconfiguration. Consequently, achieving an effective ANN hardware-based architecture so as to adapt to not only strict accuracy, enormous configures, or silicon area but also real-time criterion in pattern recognition systems has been really challenged. To tackle these issues, this work has proposed a dynamic structure of three-layer ANN architecture being able to reconfigure for adapting to various real-time applications. What is more, a complete SOPC system integrating proposed ANN hardware has also implemented to apply Vietnamese speech recognition automatically to confirm high recognition probability around 95.2 % towards 20 Vietnamese discrete words. Moreover, experiment results on such ASIC-based architecture have witnessed maximum frequency at 250 MHz on 130nm technology as well as great ability of reconfiguration.
Downloads
References
[1] B. Markovic, J. Galic, S. T. Jovicie, Application of Neural Networks in Whispered Speech Recognition, TELFOR, 2012, pp. 728-731.
[2] I. Sahin, I. Koyuncu, Design and Implementation of Neural Networks Neurons with RadBas, LogSig, and TanSigActivation Functions on FPGA, Electronics & Electrical Engineering, 2012.
[3] C. Alippi, G. StortiGajani, Simple approximation of Sigmoidal functions: realistic design of digital neural networks capable of learning, Proc. IEEE Int. Symp. on Circuits and Systems, 1991, pp. 1505-1508.
[4] H. Amin, Piecewise linear approximation applied to nonlinear function of a neural network, Circuits, Devices and Systems, 1997, pp. 313-317.
[5] M. Zhang, Sigmoid generators for neural computing using piecewise approximations, IEEE Trans. on Computers, 1996, pp. 1045-1059.
[6] Thamer M. Jame, Ban M. Khammas, Implementation of a Sigmoid activation function for neural network using FPGA, Scientific Conference of Al-Mamoon University College, 2012.
[7] Shing-Tai Pan, Chih-Chin Lai, Bo-Yu Tsai, The implementation of speech recognition systems on fpga-based embedded systems with soc architecture, Int. Jour. of Innovative Computing, Information and Control, No. 10, 2011.
[8] Khamlich S. Eddine, Hamdoun Abdellatif, Atouf Issam, Madiafi Mohammed, Serial Hardware Implementation of The MFCC and MLP Architecture on FPGA Circuit, Int. Jour. of Engineering and Technology (IJET), Vol. 5, No. 4, 2013.
[9] Boussaa Mohamed, Atouf Issam, Atibi Mohamed, Bennis Abdellatif, Comparison of Hardware and NIOS II Based Software Implementation of MLP on The FPGA Plateform, Jour. of Theoretical and Applied Information Technology, Vol.72, No.3, 2015.
[10] Dhirajkumar S. Jinde, Samrat S. Thorat, Neural Network Implementation Using FPGAs, Int. Jour. of Computer Science and Information Technologies (IJCSIT), 2014, pp. 3431-3433.
[11] Esraa Z. Mohammed and Haitham K. Ali, Hardware Implementation of Artificial Neural Network Using Field Programmable Gate Array, Int. Jour. of Computer Theory and Engineering, Vol. 5, No. 5, 2013.
[12] A. Gomperts, A. Ukil, F. Zurfluh, Development and Implementation of Parameterized FPGA Based General Purpose Neural Networks for Online Applications, IEEE Trans. on Industrial Informatics, 2011, pp. 79-89.
[13] K. Venkata Ramanaiah and C. Prasanna Raj, ASIC Implementation of Neural Network Based Image Compression, Int. Jour. of Computer Theory and Engineering, Vol. 3, No. 4, 2011.
[14] Panca M. Rahardjo, Moch. Rifan dan Nanang Sulistyanto, The Implementation of Feedforward Backpropagation Algorithm for Digit Handwritten Recognition in a Xilinx Spartan-3, Journal EECCIS, 2012, pp. 17-21.
[15] Suhap Sahin, Yasar Becerikli, and Suleyman Yazici, Neural Network Implementation in Hardware Using FPGAs, ICONIP 2006, pp. 1105-1112.
[16] Hassene Faiedh, Chokri Souani, Kholdoun Torki and Kamel Besbes, Digital Hardware Implementation of a Neural System Used for Nonlinear Adaptive Prediction, ICONIP 2006 Jour. of Computer Science, 2006, pp.355-362.
[17] Andrew Thall, Extended-Precision Floating-Point Numbers for GPU Computation, ACM SIGGRAPH 52, 2006
[18] Damak A., Krid M., Masmoudi D.S, Neural Network Based Edge Detection with Pulse Mode Operations and Floating Point Format Precision, Design and Technology of Integrated Systems in Nanoscale Era, March 2008, page 1-5, 25-27.
[19] Puneet Paruthi, Tanvi Kumar, Himanshu Singh, Simulation of IEEE 754 Standard Double Precision Multiplier using Booth Techniques, International Journal of Engineering Research and Applications (IJERA),Vol.2, September- October 2012, pp.1761-1766.
[20] Shaifali, Ms.Sakshi, Comparison of IEEE-754 Standard Single Precision Floating Point Multipliers, International Journal of Emerging Trends in Electrical and Electronics (IJETEE), Vol.1, March 2013, pp. 900-904
[21] Gokul Govindu, Ling Zhuo, Seonil Choi, Prasanna, Viktor Prasanna, Analysis of High-performance Floating- point Arithmetic on FPGAs, Parallel and Distributed Processing Symposium, April 2004
[22] Dorde T. Grozdic, Branko Markovic, Jovan Galic, Slobodan T. Jovicic, Application of Neural Networks in Whispered Speech Recognition, Telfor Journal, Vol. 5, No.2, 2013.
