A novel approach to inferring letter-phoneme correspondences

Wing Pong Robert Luk; Robert I. Damper

A novel approach to inferring letter-phoneme correspondences

Wing Pong Robert Luk, Robert I. Damper

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

An inference algorithm to obtain letter-phoneme correspondences for English using image-processing techniques is described. The main idea of the inference algorithm is to construct a table of association indices. The table is regarded as an image and image-processing algorithms are used to derive letter-phoneme correspondences. The advantages of the technique are that the association index has a theoretical basis in terms of modeling spelling and pronunciation as a homogenous Markov chain, computational demand is low, and the inference process is not dependent on the ordering of the sample. The authors have implemented both a thresholding and a minimum spanning tree technique to derive correspondences. Illustrative examples are given for each technique.

Original language	English
Title of host publication	Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Publisher	Publ by IEEE
Pages	741-744
Number of pages	4
Volume	2
ISBN (Print)	078030033
Publication status	Published - 1 Dec 1991
Event	Proceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91 - Toronto, Ont, Canada Duration: 14 May 1991 → 17 May 1991

Conference

Conference	Proceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91
Country/Territory	Canada
City	Toronto, Ont
Period	14/05/91 → 17/05/91

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Acoustics and Ultrasonics

Cite this

@inproceedings{de7b3584b578432eb43112a7545cff48,

title = "A novel approach to inferring letter-phoneme correspondences",

abstract = "An inference algorithm to obtain letter-phoneme correspondences for English using image-processing techniques is described. The main idea of the inference algorithm is to construct a table of association indices. The table is regarded as an image and image-processing algorithms are used to derive letter-phoneme correspondences. The advantages of the technique are that the association index has a theoretical basis in terms of modeling spelling and pronunciation as a homogenous Markov chain, computational demand is low, and the inference process is not dependent on the ordering of the sample. The authors have implemented both a thresholding and a minimum spanning tree technique to derive correspondences. Illustrative examples are given for each technique.",

author = "Luk, {Wing Pong Robert} and Damper, {Robert I.}",

year = "1991",

month = dec,

day = "1",

language = "English",

isbn = "078030033",

volume = "2",

pages = "741--744",

booktitle = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

publisher = "Publ by IEEE",

note = "Proceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91 ; Conference date: 14-05-1991 Through 17-05-1991",

}

A novel approach to inferring letter-phoneme correspondences. / Luk, Wing Pong Robert; Damper, Robert I.

Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. Vol. 2 Publ by IEEE, 1991. p. 741-744.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A novel approach to inferring letter-phoneme correspondences

AU - Luk, Wing Pong Robert

AU - Damper, Robert I.

PY - 1991/12/1

Y1 - 1991/12/1

N2 - An inference algorithm to obtain letter-phoneme correspondences for English using image-processing techniques is described. The main idea of the inference algorithm is to construct a table of association indices. The table is regarded as an image and image-processing algorithms are used to derive letter-phoneme correspondences. The advantages of the technique are that the association index has a theoretical basis in terms of modeling spelling and pronunciation as a homogenous Markov chain, computational demand is low, and the inference process is not dependent on the ordering of the sample. The authors have implemented both a thresholding and a minimum spanning tree technique to derive correspondences. Illustrative examples are given for each technique.

AB - An inference algorithm to obtain letter-phoneme correspondences for English using image-processing techniques is described. The main idea of the inference algorithm is to construct a table of association indices. The table is regarded as an image and image-processing algorithms are used to derive letter-phoneme correspondences. The advantages of the technique are that the association index has a theoretical basis in terms of modeling spelling and pronunciation as a homogenous Markov chain, computational demand is low, and the inference process is not dependent on the ordering of the sample. The authors have implemented both a thresholding and a minimum spanning tree technique to derive correspondences. Illustrative examples are given for each technique.

UR - http://www.scopus.com/inward/record.url?scp=0026393229&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 078030033

VL - 2

SP - 741

EP - 744

BT - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

PB - Publ by IEEE

T2 - Proceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91

Y2 - 14 May 1991 through 17 May 1991

ER -

A novel approach to inferring letter-phoneme correspondences

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this