ePrints Repository

Speech Recognition on an FPGA Using Discrete and Continuous Hidden Markov Models

Melnikoff, Stephen Jonathan and Quigley, Steven Francis and Russell, Martin (2002) Speech Recognition on an FPGA Using Discrete and Continuous Hidden Markov Models. In: Field-Programmable Logic and Applications. Reconfigurable Computing Is Going Mainstream 12th International Conference, FPL 2002, Montpellier, France September 2-4, 2002. Proceedings. Lecture Notes in Computer Science (2438). Springer Verlag, pp. 202-211. ISBN Series ISSN 0302-9743

PDF (105Kb)

URL of Published Version: http://www.springerlink.com/content/12lmfc9httabcrae

Speech recognition is a computationally demanding task, particularly the stage which uses Viterbi decoding for converting pre-processed speech data into words or sub-word units. Any device that can reduce the load on, for example, a PC’s processor, is advantageous. Hence we present FPGA implementations of the decoder based alternately on discrete and continuous hidden Markov models (HMMs) representing monophones, and demonstrate that the discrete version can process speech nearly 5,000 times real time, using just 12% of the slices of a Xilinx Virtex XCV1000, but with a lower recognition rate than the continuous implementation, which is 75 times faster than real time, and occupies 45% of the same device.

Type of Work:Book Section
Date:2002 (Publication)
School/Faculty:Schools (1998 to 2008) > School of Engineering
Department:Electronic, Electrical and Computer Engineering
Additional Information:

The original publication is available at www.springerlink.com

Subjects:TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
Institution:University of Birmingham
Copyright Holders:Springer
ID Code:26
Export Reference As : ASCII + BibTeX + Dublin Core + EndNote + HTML + METS + MODS + OpenURL Object + Reference Manager + Refer + RefWorks
Share this item :
QR Code for this page

Repository Staff Only: item control page