Implementing a Simple Continuous Speech Recognition System on an FPGA

Stephen Melnikoff; Steven Quigley; Martin Russell

Implementing a Simple Continuous Speech Recognition System on an FPGA

Stephen Melnikoff, Steven Quigley, Martin Russell

Electronic, Electrical and Systems Engineering

Research output: Contribution to conference (unpublished) › Paper › peer-review

37 Citations (Scopus)

474 Downloads (Pure)

Abstract

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. We present an FPGA implementations of the decoder based on continuous hidden Markov models (HMMs) representing monophones, and demonstrate that it can process speech 75 times real time, using 45% of the slices of a Xilinx Virtex XCV1000

Original language	English
Pages	275-276
Number of pages	2
Publication status	Published - 1 Jan 2002
Event	IEEE Symposium on Field Programmable Custom Computing Machines - Duration: 1 Jan 2002 → …

Conference

Conference	IEEE Symposium on Field Programmable Custom Computing Machines
Period	1/01/02 → …

Bibliographical note

©2002 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Access to Document

Melnikoff02FCCMpubl.pdf
IEEE
Accepted author manuscript, 344 KB

http://ieeexplore.ieee.org/iel5/8168/24313/01106682.pdf?isnumber=24313&prod=STD&arnumber=1106682&arnumber=1106682&arSt=+275&ared=+276&arAuthor=Melnikoff%2C+S.J.%3B+Quigley%2C+S.F.%3B+Russell%2C+M.J.

Cite this

Melnikoff, S., Quigley, S., & Russell, M. (2002). Implementing a Simple Continuous Speech Recognition System on an FPGA. 275-276. Paper presented at IEEE Symposium on Field Programmable Custom Computing Machines. http://ieeexplore.ieee.org/iel5/8168/24313/01106682.pdf?isnumber=24313&prod=STD&arnumber=1106682&arnumber=1106682&arSt=+275&ared=+276&arAuthor=Melnikoff%2C+S.J.%3B+Quigley%2C+S.F.%3B+Russell%2C+M.J.

@conference{78118f2ca15748b9891a5abcd1800292,

title = "Implementing a Simple Continuous Speech Recognition System on an FPGA",

abstract = "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. We present an FPGA implementations of the decoder based on continuous hidden Markov models (HMMs) representing monophones, and demonstrate that it can process speech 75 times real time, using 45% of the slices of a Xilinx Virtex XCV1000",

author = "Stephen Melnikoff and Steven Quigley and Martin Russell",

note = "{\textcopyright}2002 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; IEEE Symposium on Field Programmable Custom Computing Machines ; Conference date: 01-01-2002",

year = "2002",

month = jan,

day = "1",

language = "English",

pages = "275--276",

}

Melnikoff, S, Quigley, S & Russell, M 2002, 'Implementing a Simple Continuous Speech Recognition System on an FPGA', Paper presented at IEEE Symposium on Field Programmable Custom Computing Machines, 1/01/02 pp. 275-276. <http://ieeexplore.ieee.org/iel5/8168/24313/01106682.pdf?isnumber=24313&prod=STD&arnumber=1106682&arnumber=1106682&arSt=+275&ared=+276&arAuthor=Melnikoff%2C+S.J.%3B+Quigley%2C+S.F.%3B+Russell%2C+M.J.>

TY - CONF

T1 - Implementing a Simple Continuous Speech Recognition System on an FPGA

AU - Melnikoff, Stephen

AU - Quigley, Steven

AU - Russell, Martin

N1 - ©2002 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - 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. We present an FPGA implementations of the decoder based on continuous hidden Markov models (HMMs) representing monophones, and demonstrate that it can process speech 75 times real time, using 45% of the slices of a Xilinx Virtex XCV1000

AB - 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. We present an FPGA implementations of the decoder based on continuous hidden Markov models (HMMs) representing monophones, and demonstrate that it can process speech 75 times real time, using 45% of the slices of a Xilinx Virtex XCV1000

M3 - Paper

SP - 275

EP - 276

T2 - IEEE Symposium on Field Programmable Custom Computing Machines

Y2 - 1 January 2002

ER -

Implementing a Simple Continuous Speech Recognition System on an FPGA

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this