Implementing a Hidden Markov Model Speech Recognition System in Programmable Logic

Stephen Melnikoff, Steven Quigley, Martin Russell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)
285 Downloads (Pure)

Abstract

Performing Viterbi decoding for continuous real-time speech recognition is a highly computationally-demanding task, but is one which can take good advantage of a parallel processing architecture. To this end, we describe a system which uses an FPGA for the decoding and a PC for pre- and post-processing, taking advantage of the properties of this kind of programmable logic device, specifically its ability to perform in parallel the large number of additions and comparisons required. We compare the performance of the FPGA decoder to a software equivalent, and discuss issues related to this implementation.
Original languageEnglish
Title of host publication Field-Programmable Logic and Applications, 11th International Conference, FPL 2001. Proceedings
PublisherSpringer
Pages81-90
Number of pages10
Publication statusPublished - 1 Jan 2001
EventInternational Conference on Field-Programmable Logic and Applications -
Duration: 1 Jan 2001 → …

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume2147
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Field-Programmable Logic and Applications
Period1/01/01 → …

Bibliographical note

null

The original publication is available at www.springerlink.com

Fingerprint

Dive into the research topics of 'Implementing a Hidden Markov Model Speech Recognition System in Programmable Logic'. Together they form a unique fingerprint.

Cite this