Table of Contents Author Guidelines Submit a Manuscript
International Journal of Reconfigurable Computing
Volume 2011 (2011), Article ID 697080, 10 pages
http://dx.doi.org/10.1155/2011/697080
Research Article

FPGA Implementation of a Pipelined Gaussian Calculation for HMM-Based Large Vocabulary Speech Recognition

Electronics, Communications and Information Technology (ECIT), Queens University Belfast, Northern Ireland Science Park, Belfast BT3 9DT, UK

Received 1 June 2010; Revised 19 September 2010; Accepted 27 September 2010

Academic Editor: Gustavo Sutter

Copyright © 2011 Richard Veitch et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

A scalable large vocabulary, speaker independent speech recognition system is being developed using Hidden Markov Models (HMMs) for acoustic modeling and a Weighted Finite State Transducer (WFST) to compile sentence, word, and phoneme models. The system comprises a software backend search and an FPGA-based Gaussian calculation which are covered here. In this paper, we present an efficient pipelined design implemented both as an embedded peripheral and as a scalable, parallel hardware accelerator. Both architectures have been implemented on an Alpha Data XRC-5T1, reconfigurable computer housing a Virtex 5 SX95T FPGA. The core has been tested and is capable of calculating a full set of Gaussian results from 3825 acoustic models in 9.03 ms which coupled with a backend search of 5000 words has provided an accuracy of over 80%. Parallel implementations have been designed with up to 32 cores and have been successfully implemented with a clock frequency of 133 MHz.