Articulatory distinctiveness of vowels and consonants

A data-driven approach

Jun Wang, Jordan R. Green, Ashok K Samal, Yana Yunusova

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Purpose: To quantify the articulatory distinctiveness of 8 major English vowels and 11 English consonants based on tongue and lip movement time series data using a data-driven approach. Method: Tongue and lip movements of 8 vowels and 11 consonants from 10 healthy talkers were collected. First, classification accuracies were obtained using 2 complementary approaches: (a) Procrustes analysis and (b) a support vector machine. Procrustes distance was then used to measure the articulatory distinctiveness among vowels and consonants. Finally, the distance (distinctiveness) matrices of different vowel pairs and consonant pairs were used to derive articulatory vowel and consonant spaces using multidimensional scaling. Results: Vowel classification accuracies of 91.67% and 89.05% and consonant classification accuracies of 91.37% and 88.94% were obtained using Procrustes analysis and a support vector machine, respectively. Articulatory vowel and consonant spaces were derived based on the pairwise Procrustes distances. Conclusions: The articulatory vowel space derived in this study resembled the long-standing descriptive articulatory vowel space defined by tongue height and advancement. The articulatory consonant space was consistent with feature-based classification of English consonants. The derived articulatory vowel and consonant spaces may have clinical implications, including serving as an objective measure of the severity of articulatory impairment.

Original languageEnglish (US)
Pages (from-to)1539-1551
Number of pages13
JournalJournal of Speech, Language, and Hearing Research
Volume56
Issue number5
DOIs
StatePublished - Oct 1 2013

Fingerprint

Tongue
Lip
multidimensional scaling
time series
Data-driven
Distinctiveness
Consonant
Support Vector Machine

Keywords

  • Articulatory consonant space
  • Articulatory vowel space
  • Procrustes analysis
  • Speech production
  • Support vector machine

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Speech and Hearing

Cite this

Articulatory distinctiveness of vowels and consonants : A data-driven approach. / Wang, Jun; Green, Jordan R.; Samal, Ashok K; Yunusova, Yana.

In: Journal of Speech, Language, and Hearing Research, Vol. 56, No. 5, 01.10.2013, p. 1539-1551.

Research output: Contribution to journalArticle

@article{82d119f108e248a3a4ddbeee241d72d7,
title = "Articulatory distinctiveness of vowels and consonants: A data-driven approach",
abstract = "Purpose: To quantify the articulatory distinctiveness of 8 major English vowels and 11 English consonants based on tongue and lip movement time series data using a data-driven approach. Method: Tongue and lip movements of 8 vowels and 11 consonants from 10 healthy talkers were collected. First, classification accuracies were obtained using 2 complementary approaches: (a) Procrustes analysis and (b) a support vector machine. Procrustes distance was then used to measure the articulatory distinctiveness among vowels and consonants. Finally, the distance (distinctiveness) matrices of different vowel pairs and consonant pairs were used to derive articulatory vowel and consonant spaces using multidimensional scaling. Results: Vowel classification accuracies of 91.67{\%} and 89.05{\%} and consonant classification accuracies of 91.37{\%} and 88.94{\%} were obtained using Procrustes analysis and a support vector machine, respectively. Articulatory vowel and consonant spaces were derived based on the pairwise Procrustes distances. Conclusions: The articulatory vowel space derived in this study resembled the long-standing descriptive articulatory vowel space defined by tongue height and advancement. The articulatory consonant space was consistent with feature-based classification of English consonants. The derived articulatory vowel and consonant spaces may have clinical implications, including serving as an objective measure of the severity of articulatory impairment.",
keywords = "Articulatory consonant space, Articulatory vowel space, Procrustes analysis, Speech production, Support vector machine",
author = "Jun Wang and Green, {Jordan R.} and Samal, {Ashok K} and Yana Yunusova",
year = "2013",
month = "10",
day = "1",
doi = "10.1044/1092-4388(2013/12-0030)",
language = "English (US)",
volume = "56",
pages = "1539--1551",
journal = "Journal of Speech, Language, and Hearing Research",
issn = "1092-4388",
publisher = "American Speech-Language-Hearing Association (ASHA)",
number = "5",

}

TY - JOUR

T1 - Articulatory distinctiveness of vowels and consonants

T2 - A data-driven approach

AU - Wang, Jun

AU - Green, Jordan R.

AU - Samal, Ashok K

AU - Yunusova, Yana

PY - 2013/10/1

Y1 - 2013/10/1

N2 - Purpose: To quantify the articulatory distinctiveness of 8 major English vowels and 11 English consonants based on tongue and lip movement time series data using a data-driven approach. Method: Tongue and lip movements of 8 vowels and 11 consonants from 10 healthy talkers were collected. First, classification accuracies were obtained using 2 complementary approaches: (a) Procrustes analysis and (b) a support vector machine. Procrustes distance was then used to measure the articulatory distinctiveness among vowels and consonants. Finally, the distance (distinctiveness) matrices of different vowel pairs and consonant pairs were used to derive articulatory vowel and consonant spaces using multidimensional scaling. Results: Vowel classification accuracies of 91.67% and 89.05% and consonant classification accuracies of 91.37% and 88.94% were obtained using Procrustes analysis and a support vector machine, respectively. Articulatory vowel and consonant spaces were derived based on the pairwise Procrustes distances. Conclusions: The articulatory vowel space derived in this study resembled the long-standing descriptive articulatory vowel space defined by tongue height and advancement. The articulatory consonant space was consistent with feature-based classification of English consonants. The derived articulatory vowel and consonant spaces may have clinical implications, including serving as an objective measure of the severity of articulatory impairment.

AB - Purpose: To quantify the articulatory distinctiveness of 8 major English vowels and 11 English consonants based on tongue and lip movement time series data using a data-driven approach. Method: Tongue and lip movements of 8 vowels and 11 consonants from 10 healthy talkers were collected. First, classification accuracies were obtained using 2 complementary approaches: (a) Procrustes analysis and (b) a support vector machine. Procrustes distance was then used to measure the articulatory distinctiveness among vowels and consonants. Finally, the distance (distinctiveness) matrices of different vowel pairs and consonant pairs were used to derive articulatory vowel and consonant spaces using multidimensional scaling. Results: Vowel classification accuracies of 91.67% and 89.05% and consonant classification accuracies of 91.37% and 88.94% were obtained using Procrustes analysis and a support vector machine, respectively. Articulatory vowel and consonant spaces were derived based on the pairwise Procrustes distances. Conclusions: The articulatory vowel space derived in this study resembled the long-standing descriptive articulatory vowel space defined by tongue height and advancement. The articulatory consonant space was consistent with feature-based classification of English consonants. The derived articulatory vowel and consonant spaces may have clinical implications, including serving as an objective measure of the severity of articulatory impairment.

KW - Articulatory consonant space

KW - Articulatory vowel space

KW - Procrustes analysis

KW - Speech production

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84886644229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886644229&partnerID=8YFLogxK

U2 - 10.1044/1092-4388(2013/12-0030)

DO - 10.1044/1092-4388(2013/12-0030)

M3 - Article

VL - 56

SP - 1539

EP - 1551

JO - Journal of Speech, Language, and Hearing Research

JF - Journal of Speech, Language, and Hearing Research

SN - 1092-4388

IS - 5

ER -