Title :
Analogue radial basis function networks for phoneme recognition
Author :
Gatt, E. ; Micallef, J.
Author_Institution :
Dept. of Microelectron., Univ. of Malta, Msida, Malta
Abstract :
This paper presents an analogue radial basis function neural network for phoneme recognition. The neural network has been implemented on-chip using 0.35 μm three-metal dual-poly CMOS technology. Radial basis function neural networks have been adopted because they offer improved training times when compared to multi-layer perceptron networks implementing conventional back-propagation learning (S. Renals and R. Rohwer, Proc. IEEE/INNS First Inter. Joint Conf. Neural Networks, vol. 1, pp. 461-467, 1997). The paper also presents the performance characteristics for the chip, together with its application to the problem of phoneme recognition.
Keywords :
CMOS analogue integrated circuits; analogue simulation; circuit simulation; integrated circuit design; integrated circuit modelling; neural chips; radial basis function networks; speech recognition equipment; 0.35 micron; CMOS analogue radial basis function neural networks; back-propagation learning; multi-layer perceptron networks; phoneme recognition; speech recognition; three-metal dual-poly CMOS technology; training time improvement; CMOS technology; Computer networks; Information technology; Kernel; Mathematics; Microelectronics; Network-on-a-chip; Neural networks; Radial basis function networks; Supervised learning;
Conference_Titel :
Electronics, Circuits and Systems, 2002. 9th International Conference on
Print_ISBN :
0-7803-7596-3
DOI :
10.1109/ICECS.2002.1046234
