Using Landmark Detection to measure effective Clear Speech

Suzanne Boyce*, Jean Krause, Sarah Hamilton, Rajka Smiljanic, Ann R. Bradlow, Ahmed Rivera-Campos, Joel MacAuslan

*Corresponding author for this work

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

While the relationship of clear speaking style to intelligibility under challenging conditions has been established, it is a common observation that some speakers seem to be more intelligible than others for most listeners. In previous work, we have reported that automatic measures based on the technique of Landmark Detection appear to track differences between Clear and Conversational speaking style. One question that remains is whether Landmark measures can be used to predict which speakers are most likely to produce highly intelligible speech. In this study, we took advantage of a set of previously acquired databases to examine correlations between our Landmark-based measures and the Clear Speech productions of highly intelligible speech. Across these databases, we had data on intelligibility for a range of speakers. Results showed that speakers with high overall intelligibility in Clear Speech showed significantly different patterns on Landmark-based automatic measures, compared to speakers with more moderate performance on intelligibility measures. Applications of these results to problems in speech technology, linguistic education and clinical practice will be discussed.

Original languageEnglish (US)
Article number060129
JournalProceedings of Meetings on Acoustics
Volume19
DOIs
StatePublished - Jun 19 2013
Event21st International Congress on Acoustics, ICA 2013 - 165th Meeting of the Acoustical Society of America - Montreal, QC, Canada
Duration: Jun 2 2013Jun 7 2013

Fingerprint

landmarks
intelligibility
linguistics
education

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

Boyce, S., Krause, J., Hamilton, S., Smiljanic, R., Bradlow, A. R., Rivera-Campos, A., & MacAuslan, J. (2013). Using Landmark Detection to measure effective Clear Speech. Proceedings of Meetings on Acoustics, 19, [060129]. https://doi.org/10.1121/1.4800680
Boyce, Suzanne ; Krause, Jean ; Hamilton, Sarah ; Smiljanic, Rajka ; Bradlow, Ann R. ; Rivera-Campos, Ahmed ; MacAuslan, Joel. / Using Landmark Detection to measure effective Clear Speech. In: Proceedings of Meetings on Acoustics. 2013 ; Vol. 19.
@article{687af044662e460abcd3d137d8fe17d7,
title = "Using Landmark Detection to measure effective Clear Speech",
abstract = "While the relationship of clear speaking style to intelligibility under challenging conditions has been established, it is a common observation that some speakers seem to be more intelligible than others for most listeners. In previous work, we have reported that automatic measures based on the technique of Landmark Detection appear to track differences between Clear and Conversational speaking style. One question that remains is whether Landmark measures can be used to predict which speakers are most likely to produce highly intelligible speech. In this study, we took advantage of a set of previously acquired databases to examine correlations between our Landmark-based measures and the Clear Speech productions of highly intelligible speech. Across these databases, we had data on intelligibility for a range of speakers. Results showed that speakers with high overall intelligibility in Clear Speech showed significantly different patterns on Landmark-based automatic measures, compared to speakers with more moderate performance on intelligibility measures. Applications of these results to problems in speech technology, linguistic education and clinical practice will be discussed.",
author = "Suzanne Boyce and Jean Krause and Sarah Hamilton and Rajka Smiljanic and Bradlow, {Ann R.} and Ahmed Rivera-Campos and Joel MacAuslan",
year = "2013",
month = "6",
day = "19",
doi = "10.1121/1.4800680",
language = "English (US)",
volume = "19",
journal = "Proceedings of Meetings on Acoustics",
issn = "1939-800X",
publisher = "Acoustical Society of America",

}

Boyce, S, Krause, J, Hamilton, S, Smiljanic, R, Bradlow, AR, Rivera-Campos, A & MacAuslan, J 2013, 'Using Landmark Detection to measure effective Clear Speech', Proceedings of Meetings on Acoustics, vol. 19, 060129. https://doi.org/10.1121/1.4800680

Using Landmark Detection to measure effective Clear Speech. / Boyce, Suzanne; Krause, Jean; Hamilton, Sarah; Smiljanic, Rajka; Bradlow, Ann R.; Rivera-Campos, Ahmed; MacAuslan, Joel.

In: Proceedings of Meetings on Acoustics, Vol. 19, 060129, 19.06.2013.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Using Landmark Detection to measure effective Clear Speech

AU - Boyce, Suzanne

AU - Krause, Jean

AU - Hamilton, Sarah

AU - Smiljanic, Rajka

AU - Bradlow, Ann R.

AU - Rivera-Campos, Ahmed

AU - MacAuslan, Joel

PY - 2013/6/19

Y1 - 2013/6/19

N2 - While the relationship of clear speaking style to intelligibility under challenging conditions has been established, it is a common observation that some speakers seem to be more intelligible than others for most listeners. In previous work, we have reported that automatic measures based on the technique of Landmark Detection appear to track differences between Clear and Conversational speaking style. One question that remains is whether Landmark measures can be used to predict which speakers are most likely to produce highly intelligible speech. In this study, we took advantage of a set of previously acquired databases to examine correlations between our Landmark-based measures and the Clear Speech productions of highly intelligible speech. Across these databases, we had data on intelligibility for a range of speakers. Results showed that speakers with high overall intelligibility in Clear Speech showed significantly different patterns on Landmark-based automatic measures, compared to speakers with more moderate performance on intelligibility measures. Applications of these results to problems in speech technology, linguistic education and clinical practice will be discussed.

AB - While the relationship of clear speaking style to intelligibility under challenging conditions has been established, it is a common observation that some speakers seem to be more intelligible than others for most listeners. In previous work, we have reported that automatic measures based on the technique of Landmark Detection appear to track differences between Clear and Conversational speaking style. One question that remains is whether Landmark measures can be used to predict which speakers are most likely to produce highly intelligible speech. In this study, we took advantage of a set of previously acquired databases to examine correlations between our Landmark-based measures and the Clear Speech productions of highly intelligible speech. Across these databases, we had data on intelligibility for a range of speakers. Results showed that speakers with high overall intelligibility in Clear Speech showed significantly different patterns on Landmark-based automatic measures, compared to speakers with more moderate performance on intelligibility measures. Applications of these results to problems in speech technology, linguistic education and clinical practice will be discussed.

UR - http://www.scopus.com/inward/record.url?scp=84879002170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879002170&partnerID=8YFLogxK

U2 - 10.1121/1.4800680

DO - 10.1121/1.4800680

M3 - Conference article

AN - SCOPUS:84879002170

VL - 19

JO - Proceedings of Meetings on Acoustics

JF - Proceedings of Meetings on Acoustics

SN - 1939-800X

M1 - 060129

ER -

Boyce S, Krause J, Hamilton S, Smiljanic R, Bradlow AR, Rivera-Campos A et al. Using Landmark Detection to measure effective Clear Speech. Proceedings of Meetings on Acoustics. 2013 Jun 19;19. 060129. https://doi.org/10.1121/1.4800680