FPGA implementation of a pipelined Gaussian calculation for HMM-based large vocabulary speech recognition

Richard Veitch*, Louis-Marie Aubert, Roger Woods, Scott Fischaber

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
218 Downloads (Pure)

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.

Original languageEnglish
Article number697080
JournalInternational Journal of Reconfigurable Computing
Volume2011
DOIs
Publication statusPublished - 25 Nov 2010

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'FPGA implementation of a pipelined Gaussian calculation for HMM-based large vocabulary speech recognition'. Together they form a unique fingerprint.

Cite this