Application of continuous state Hidden Markov Models to a classical problem in speech recognition

Colin Champion; Stephen Houghton

doi:10.1016/j.csl.2015.05.001

Application of continuous state Hidden Markov Models to a classical problem in speech recognition

Colin Champion, Stephen Houghton

Electronic, Electrical and Systems Engineering

Research output: Contribution to journal › Article › peer-review

18 Citations (Scopus)

266 Downloads (Pure)

Abstract

This paper describes an optimal algorithm using continuous state Hidden Markov Models for solving the HMS decoding problem, which is the problem of recovering an underlying sequence of phonetic units from measurements of smoothly varying acoustic features, thus inverting the speech generation process described by Holmes, Mattingly and Shearme in a well known paper (Speech synthesis by rule. Lang. Speech 7 (1964)).

Original language	English
Pages (from-to)	347-364
Journal	Computer Speech and Language
Volume	36
Early online date	14 May 2015
DOIs	https://doi.org/10.1016/j.csl.2015.05.001
Publication status	Published - Mar 2016

Keywords

Speech recognition
Hidden Markov Model
Recognition by synthesis

Access to Document

10.1016/j.csl.2015.05.001

Champion_Houghton_Application_continuous_state_Computer_Speech_Language_2015
NOTICE: this is the author’s version of a work that was accepted for publication in Computer Speech and Language. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Computer Speech and Language, DOI: 10.1016/j.csl.2015.05.001. After an embargo period this article is subject to the terms and conditions of a Creative Commons Non-Commercial No-Derivatives license. Eligibility for repository checked June 2015
Accepted author manuscript, 1.31 MBLicence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

Cite this

@article{d09c9db1f7a94667b6a09bc89368a8f9,

title = "Application of continuous state Hidden Markov Models to a classical problem in speech recognition",

abstract = "This paper describes an optimal algorithm using continuous state Hidden Markov Models for solving the HMS decoding problem, which is the problem of recovering an underlying sequence of phonetic units from measurements of smoothly varying acoustic features, thus inverting the speech generation process described by Holmes, Mattingly and Shearme in a well known paper (Speech synthesis by rule. Lang. Speech 7 (1964)).",

keywords = "Speech recognition, Hidden Markov Model, Recognition by synthesis",

author = "Colin Champion and Stephen Houghton",

year = "2016",

month = mar,

doi = "10.1016/j.csl.2015.05.001",

language = "English",

volume = "36",

pages = "347--364",

journal = "Computer Speech and Language",

issn = "0885-2308",

publisher = "Elsevier",

}

TY - JOUR

T1 - Application of continuous state Hidden Markov Models to a classical problem in speech recognition

AU - Champion, Colin

AU - Houghton, Stephen

PY - 2016/3

Y1 - 2016/3

N2 - This paper describes an optimal algorithm using continuous state Hidden Markov Models for solving the HMS decoding problem, which is the problem of recovering an underlying sequence of phonetic units from measurements of smoothly varying acoustic features, thus inverting the speech generation process described by Holmes, Mattingly and Shearme in a well known paper (Speech synthesis by rule. Lang. Speech 7 (1964)).

AB - This paper describes an optimal algorithm using continuous state Hidden Markov Models for solving the HMS decoding problem, which is the problem of recovering an underlying sequence of phonetic units from measurements of smoothly varying acoustic features, thus inverting the speech generation process described by Holmes, Mattingly and Shearme in a well known paper (Speech synthesis by rule. Lang. Speech 7 (1964)).

KW - Speech recognition

KW - Hidden Markov Model

KW - Recognition by synthesis

U2 - 10.1016/j.csl.2015.05.001

DO - 10.1016/j.csl.2015.05.001

M3 - Article

SN - 0885-2308

VL - 36

SP - 347

EP - 364

JO - Computer Speech and Language

JF - Computer Speech and Language

ER -

Application of continuous state Hidden Markov Models to a classical problem in speech recognition

Abstract

Keywords

Access to Document

Fingerprint

Cite this