Ghent University Academic Bibliography

Advanced

Combining phonological and acoustic ASR-free features for pathological speech intelligibility assessment

Catherine Middag UGent, Tobias Bocklet, Jean-Pierre Martens UGent and Elmar Nöth (2011) Proceedings of the 12th annual conference of the International Speech Communication Association (Interspeech 2011). p.3005-3008
abstract
Intelligibility is widely used to measure the severity of articulatory problems in pathological speech. Recently, a number of automatic intelligibility assessment tools have been developed. Most of them use automatic speech recognizers (ASR) to compare the patient's utterance with the target text. These methods are bound to one language and tend to be less accurate when speakers hesitate or make reading errors. To circumvent these problems, two different ASR-free methods were developed over the last few years, only making use of the acoustic or phonological properties of the utterance. In this paper, we demonstrate that these ASR-free techniques are also able to predict intelligibility in other languages. Moreover, they show to be complementary, resulting in even better intelligibility predictions when both methods are combined.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
ASR, phonological, pathological speech
in
Proceedings of the 12th annual conference of the International Speech Communication Association (Interspeech 2011)
pages
3005 - 3008
publisher
International Speech Communication Association (ISCA)
conference name
12th Annual conference of the International Speech Communication Association (Interspeech 2011)
conference location
Florence, Italy
conference start
2011-08-27
conference end
2011-08-31
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
1960865
handle
http://hdl.handle.net/1854/LU-1960865
date created
2011-12-06 14:14:54
date last changed
2011-12-07 09:09:47
@inproceedings{1960865,
  abstract     = {Intelligibility is widely used to measure the severity of articulatory problems in pathological speech.  Recently, a number of automatic intelligibility assessment tools have been developed.  Most of them use automatic speech recognizers (ASR) to compare the patient's utterance with the target text. These methods are bound to one language and tend to be less accurate when speakers hesitate or make reading errors.  To circumvent these problems, two different ASR-free methods were developed over the last few years, only making use of the acoustic or phonological properties of the utterance. In this paper, we demonstrate that these ASR-free techniques are also able to predict intelligibility in other languages.  Moreover, they show to be complementary, resulting in even better intelligibility predictions when both methods are combined.},
  author       = {Middag, Catherine and Bocklet, Tobias and Martens, Jean-Pierre and N{\"o}th, Elmar},
  booktitle    = {Proceedings of the 12th annual conference of the International Speech Communication Association (Interspeech 2011)},
  keyword      = {ASR,phonological,pathological speech},
  language     = {eng},
  location     = {Florence, Italy},
  pages        = {3005--3008},
  publisher    = {International Speech Communication Association (ISCA)},
  title        = {Combining phonological and acoustic ASR-free features for pathological speech intelligibility assessment},
  year         = {2011},
}

Chicago
Middag, Catherine, Tobias Bocklet, Jean-Pierre Martens, and Elmar Nöth. 2011. “Combining Phonological and Acoustic ASR-free Features for Pathological Speech Intelligibility Assessment.” In Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech 2011), 3005–3008. International Speech Communication Association (ISCA).
APA
Middag, C., Bocklet, T., Martens, J.-P., & Nöth, E. (2011). Combining phonological and acoustic ASR-free features for pathological speech intelligibility assessment. Proceedings of the 12th annual conference of the International Speech Communication Association (Interspeech 2011) (pp. 3005–3008). Presented at the 12th Annual conference of the International Speech Communication Association (Interspeech 2011), International Speech Communication Association (ISCA).
Vancouver
1.
Middag C, Bocklet T, Martens J-P, Nöth E. Combining phonological and acoustic ASR-free features for pathological speech intelligibility assessment. Proceedings of the 12th annual conference of the International Speech Communication Association (Interspeech 2011). International Speech Communication Association (ISCA); 2011. p. 3005–8.
MLA
Middag, Catherine, Tobias Bocklet, Jean-Pierre Martens, et al. “Combining Phonological and Acoustic ASR-free Features for Pathological Speech Intelligibility Assessment.” Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech 2011). International Speech Communication Association (ISCA), 2011. 3005–3008. Print.