Advanced search
1 file | 129.60 KB

Towards an ASR-free objective analysis of pathological speech

Catherine Middag (UGent), Yvan Saeys (UGent) and Jean-Pierre Martens (UGent)
(2010) INTERSPEECH. 2010. p.294-297
Author
Organization
Abstract
Nowadays, intelligibility is a popular measure of the severity of the articulatory deficiencies of a pathological speaker. Usually, this measure is obtained by means of a perceptual test, consisting of nonconventional and/or nonconnected words. In previous work, we developed a system incorporating two Automatic Speech Recognizers (ASR) that could fairly accurately estimate phoneme intelligibility (PI). In the present paper, we propose a novel method that aims to assess the running speech intelligibility (RSI) as a more relevant indicator of the communication efficiency of a speaker in a natural setting. The proposed method computes a phonological characterization of the speaker by means of a statistical analysis of frame-level phonological features. Important is that this analysis requires no knowledge of what the speaker was supposed to say. The new characterization is demonstrated to predict PI and to provide valuable information about the nature and severity of the pathology.
Keywords
objective intelligibility assessment, pathological speech, running speech, phonological features

Downloads

    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 129.60 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Middag, Catherine, Yvan Saeys, and Jean-Pierre Martens. 2010. “Towards an ASR-free Objective Analysis of Pathological Speech.” In Interspeech, 2010:294–297. Baixas, France: International Speech Communication Association (ISCA).
APA
Middag, C., Saeys, Y., & Martens, J.-P. (2010). Towards an ASR-free objective analysis of pathological speech. INTERSPEECH (Vol. 2010, pp. 294–297). Presented at the 11th Annual conference of the International Speech Communication Association (Interspeech 2010), Baixas, France: International Speech Communication Association (ISCA).
Vancouver
1.
Middag C, Saeys Y, Martens J-P. Towards an ASR-free objective analysis of pathological speech. INTERSPEECH. Baixas, France: International Speech Communication Association (ISCA); 2010. p. 294–7.
MLA
Middag, Catherine, Yvan Saeys, and Jean-Pierre Martens. “Towards an ASR-free Objective Analysis of Pathological Speech.” Interspeech. Vol. 2010. Baixas, France: International Speech Communication Association (ISCA), 2010. 294–297. Print.
@inproceedings{1053399,
  abstract     = {Nowadays, intelligibility is a popular measure of the severity of the articulatory deficiencies of a pathological speaker. Usually, this measure is obtained by means of a perceptual test, consisting of nonconventional and/or nonconnected words. In previous work, we developed a system incorporating two Automatic Speech Recognizers (ASR) that could fairly accurately estimate phoneme intelligibility (PI). In the present paper, we propose a novel method that aims to assess the running speech intelligibility (RSI) as a more relevant indicator of the communication efficiency of a speaker in a natural setting. The proposed method computes a phonological characterization of the speaker by means of a statistical analysis of frame-level phonological features. Important is that this analysis requires no knowledge of what the speaker was supposed to say. The new characterization is demonstrated to predict PI and to provide valuable information about the nature and severity of the pathology.},
  author       = {Middag, Catherine and Saeys, Yvan and Martens, Jean-Pierre},
  booktitle    = {INTERSPEECH},
  isbn         = {9781617821233},
  issn         = {1990-9772},
  keyword      = {objective intelligibility assessment,pathological speech,running speech,phonological features},
  language     = {eng},
  location     = {Makuhari, Chiba, Japan},
  pages        = {294--297},
  publisher    = {International Speech Communication Association (ISCA)},
  title        = {Towards an ASR-free objective analysis of pathological speech},
  volume       = {2010},
  year         = {2010},
}

Web of Science
Times cited: