Title: Automatic speech recognition systems: challenges and recent implementation trends

Authors: Davinder Pal Sharma; Jamin Atkins

Addresses: VLSI Research Laboratory, Department of Physics, The University of the West Indies, St. Augustine, Trinidad and Tobago ' VLSI Research Laboratory, Department of Physics, The University of the West Indies, St. Augustine, Trinidad and Tobago

Abstract: Speech recognition is one of the next generation technologies for human-computer interaction. Speech recognition has been researched since the late 1950s but due to its computational complexity and limited computing capabilities of the last few decades, its progress has been impeded. In laboratory settings automatic speech recognition systems (ASR) have achieved high levels of recognition accuracies, which tend to degrade in real world environments. This paper analyses the basics of the speech recognition system. Major problems faced by ASR in real world environments have been discussed with major focus on the techniques used in the development of noise robust ASR. Throughout the years there have been different implementation mediums for ASR but Field Programmable Gate Arrays (FPGAs) seems to provide a unique advantage for the implementation of Digital Signal Processing (DSP) systems and by extension ASR systems.

Keywords: ASR; automatic speech recognition; DSP; digital signal processing; FPGA; field programmable gate arrays; Matlab; FFT; fast Fourier transform; human-computer interaction; HCI.

DOI: 10.1504/IJSISE.2014.066600

International Journal of Signal and Imaging Systems Engineering, 2014 Vol.7 No.4, pp.220 - 234

Accepted: 30 May 2013
Published online: 29 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article