PortalPublikationenObjective vs. subjective evaluation of speakers with and wit...

Objective vs. subjective evaluation of speakers with and without complete dentures

Standard

Objective vs. subjective evaluation of speakers with and without complete dentures. / Haderlein, Tino; Bocklet, Tobias; Maier, Andreas; Nöth, Elmar; Knipfer, Christian; Stelzle, Florian.

in: LECT NOTES COMPUT SC, 2009, S. 170-177.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › Konferenzaufsatz in Fachzeitschrift › Forschung › Begutachtung

Harvard

Haderlein, T, Bocklet, T, Maier, A, Nöth, E, Knipfer, C & Stelzle, F 2009, 'Objective vs. subjective evaluation of speakers with and without complete dentures', LECT NOTES COMPUT SC, S. 170-177. https://doi.org/10.1007/978-3-642-04208-9_26

APA

Haderlein, T., Bocklet, T., Maier, A., Nöth, E., Knipfer, C., & Stelzle, F. (2009). Objective vs. subjective evaluation of speakers with and without complete dentures. LECT NOTES COMPUT SC, 170-177. https://doi.org/10.1007/978-3-642-04208-9_26

Vancouver

Haderlein T, Bocklet T, Maier A, Nöth E, Knipfer C, Stelzle F. Objective vs. subjective evaluation of speakers with and without complete dentures. LECT NOTES COMPUT SC. 2009;170-177. https://doi.org/10.1007/978-3-642-04208-9_26

Bibtex

@article{4bcafa63111443b1b9266c3ee41b284b,
title = "Objective vs. subjective evaluation of speakers with and without complete dentures",
abstract = "For dento-oral rehabilitation of edentulous (toothless) patients, speech intelligibility is an important criterion. 28 persons read a standardized text once with and once without wearing complete dentures. Six experienced raters evaluated the intelligibility subjectively on a 5-point scale and the voice on the 4-point Roughness-Breathiness-Hoarseness (RBH) scales. Objective evaluation was performed by Support Vector Regression (SVR) on the word accuracy (WA) and word recognition rate (WR) of a speech recognition system, and a set of 95 word based prosodic features. The word accuracy combined with selected prosodic features showed a correlation of up to r = 0.65 to the subjective ratings for patients with dentures and r = 0.72 for patients without dentures. For the RBH scales, however, the average correlation of the feature subsets to the subjective ratings for both types of recordings was r < 0.4.",
author = "Tino Haderlein and Tobias Bocklet and Andreas Maier and Elmar N{\"o}th and Christian Knipfer and Florian Stelzle",
note = "Copyright: Copyright 2009 Elsevier B.V., All rights reserved.; 12th International Conference on Text, Speech and Dialogue, TSD 2009 ; Conference date: 13-09-2009 Through 17-09-2009",
year = "2009",
doi = "10.1007/978-3-642-04208-9_26",
language = "English",
pages = "170--177",
journal = "LECT NOTES COMPUT SC",
issn = "0302-9743",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - Objective vs. subjective evaluation of speakers with and without complete dentures

AU - Haderlein, Tino

AU - Bocklet, Tobias

AU - Maier, Andreas

AU - Nöth, Elmar

AU - Knipfer, Christian

AU - Stelzle, Florian

N1 - Copyright: Copyright 2009 Elsevier B.V., All rights reserved.

PY - 2009

Y1 - 2009

N2 - For dento-oral rehabilitation of edentulous (toothless) patients, speech intelligibility is an important criterion. 28 persons read a standardized text once with and once without wearing complete dentures. Six experienced raters evaluated the intelligibility subjectively on a 5-point scale and the voice on the 4-point Roughness-Breathiness-Hoarseness (RBH) scales. Objective evaluation was performed by Support Vector Regression (SVR) on the word accuracy (WA) and word recognition rate (WR) of a speech recognition system, and a set of 95 word based prosodic features. The word accuracy combined with selected prosodic features showed a correlation of up to r = 0.65 to the subjective ratings for patients with dentures and r = 0.72 for patients without dentures. For the RBH scales, however, the average correlation of the feature subsets to the subjective ratings for both types of recordings was r < 0.4.

AB - For dento-oral rehabilitation of edentulous (toothless) patients, speech intelligibility is an important criterion. 28 persons read a standardized text once with and once without wearing complete dentures. Six experienced raters evaluated the intelligibility subjectively on a 5-point scale and the voice on the 4-point Roughness-Breathiness-Hoarseness (RBH) scales. Objective evaluation was performed by Support Vector Regression (SVR) on the word accuracy (WA) and word recognition rate (WR) of a speech recognition system, and a set of 95 word based prosodic features. The word accuracy combined with selected prosodic features showed a correlation of up to r = 0.65 to the subjective ratings for patients with dentures and r = 0.72 for patients without dentures. For the RBH scales, however, the average correlation of the feature subsets to the subjective ratings for both types of recordings was r < 0.4.

UR - http://www.scopus.com/inward/record.url?scp=70349863092&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-04208-9_26

DO - 10.1007/978-3-642-04208-9_26

M3 - Conference article in journal

AN - SCOPUS:70349863092

SP - 170

EP - 177

JO - LECT NOTES COMPUT SC

JF - LECT NOTES COMPUT SC

SN - 0302-9743

T2 - 12th International Conference on Text, Speech and Dialogue, TSD 2009

Y2 - 13 September 2009 through 17 September 2009

ER -