Structural Representation of Speech for Phonetic Classification

Alexander Gutkin; Simon King

doi:10.1109/ICPR.2004.1334560

Structural Representation of Speech for Phonetic Classification

Alexander Gutkin, Simon King

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper explores the issues involved in using symbolic metric algorithms for automatic speech recognition (ASR), via a structural representation of speech. This representation is based on a set of phonological distinctive features which is a linguistically well-motivated alternative to the ``beads-on-a-string'' view of speech that is standard in current ASR systems. We report the promising results of phoneme classification experiments conducted on a standard continuous speech task.

Original language	English
Title of host publication	Proceedings of the 17th International Conference on Pattern Recognition, 2004 (ICPR 2004)
Place of Publication	Cambridge, UK
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	438-441
Number of pages	4
Volume	3
ISBN (Print)	0769521282
DOIs	https://doi.org/10.1109/ICPR.2004.1334560
Publication status	Published - 1 Aug 2004

Access to Document

10.1109/ICPR.2004.1334560

1 Finished

ROPA: SPEECH RECOGNITION
King, S.
EPSRC
1/10/99 → 31/01/02
Project: Research

Cite this

@inproceedings{80ae7164d7d342068c02a43843977a2e,

title = "Structural Representation of Speech for Phonetic Classification",

abstract = "This paper explores the issues involved in using symbolic metric algorithms for automatic speech recognition (ASR), via a structural representation of speech. This representation is based on a set of phonological distinctive features which is a linguistically well-motivated alternative to the ``beads-on-a-string'' view of speech that is standard in current ASR systems. We report the promising results of phoneme classification experiments conducted on a standard continuous speech task.",

author = "Alexander Gutkin and Simon King",

year = "2004",

month = aug,

day = "1",

doi = "10.1109/ICPR.2004.1334560",

language = "English",

isbn = "0769521282",

volume = "3",

pages = "438--441",

booktitle = "Proceedings of the 17th International Conference on Pattern Recognition, 2004 (ICPR 2004)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Structural Representation of Speech for Phonetic Classification. / Gutkin, Alexander; King, Simon.

Proceedings of the 17th International Conference on Pattern Recognition, 2004 (ICPR 2004). Vol. 3 Cambridge, UK : Institute of Electrical and Electronics Engineers (IEEE), 2004. p. 438-441.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Structural Representation of Speech for Phonetic Classification

AU - Gutkin, Alexander

AU - King, Simon

PY - 2004/8/1

Y1 - 2004/8/1

N2 - This paper explores the issues involved in using symbolic metric algorithms for automatic speech recognition (ASR), via a structural representation of speech. This representation is based on a set of phonological distinctive features which is a linguistically well-motivated alternative to the ``beads-on-a-string'' view of speech that is standard in current ASR systems. We report the promising results of phoneme classification experiments conducted on a standard continuous speech task.

AB - This paper explores the issues involved in using symbolic metric algorithms for automatic speech recognition (ASR), via a structural representation of speech. This representation is based on a set of phonological distinctive features which is a linguistically well-motivated alternative to the ``beads-on-a-string'' view of speech that is standard in current ASR systems. We report the promising results of phoneme classification experiments conducted on a standard continuous speech task.

U2 - 10.1109/ICPR.2004.1334560

DO - 10.1109/ICPR.2004.1334560

M3 - Conference contribution

SN - 0769521282

VL - 3

SP - 438

EP - 441

BT - Proceedings of the 17th International Conference on Pattern Recognition, 2004 (ICPR 2004)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Cambridge, UK

ER -

Structural Representation of Speech for Phonetic Classification

Abstract

Access to Document

Fingerprint

Projects

ROPA: SPEECH RECOGNITION

Cite this