A System for Detecting Miscues in Dyslexic Read Speech

Morten Højfeldt Rasmussen, Zheng-Hua Tan, Børge Lindberg, Søren Holdt Jensen

Research output: Contribution to journalConference article in JournalResearchpeer-review

1 Citation (Scopus)
449 Downloads (Pure)

Abstract

While miscue detection in general is a well explored research field little attention has so far been paid to miscue detection in dyslexic read speech. This domain differs substantially from the domains that are commonly researched, as for example dyslexic read speech includes frequent regressions and long pauses between words. A system detecting miscues in dyslexic read speech is presented. It includes an ASR component employing a forced-alignment like grammar adjusted for dyslexic input and uses the GOP score and phone duration to accept or reject the read words. Experimental results show that the system detects miscues at a false alarm rate of 5.3% and a miscue detection rate of 40.1%. These results are worse than current state of the art reading tutors perhaps indicating that dyslexic read speech is a challenge to handle.
Original languageEnglish
JournalProceedings of the International Conference on Spoken Language Processing
Number of pages4
ISSN1990-9772
Publication statusPublished - 2009
EventInterspeech - Brighton, United Kingdom
Duration: 6 Sep 200910 Sep 2009
Conference number: 10

Conference

ConferenceInterspeech
Number10
CountryUnited Kingdom
CityBrighton
Period06/09/200910/09/2009

Keywords

  • miscue detection
  • reading tutor
  • dyslexia
  • speechrecognition
  • confidence score

Cite this

@inproceedings{8eca43608be711de90ca000ea68e967b,
title = "A System for Detecting Miscues in Dyslexic Read Speech",
abstract = "While miscue detection in general is a well explored research field little attention has so far been paid to miscue detection in dyslexic read speech. This domain differs substantially from the domains that are commonly researched, as for example dyslexic read speech includes frequent regressions and long pauses between words. A system detecting miscues in dyslexic read speech is presented. It includes an ASR component employing a forced-alignment like grammar adjusted for dyslexic input and uses the GOP score and phone duration to accept or reject the read words. Experimental results show that the system detects miscues at a false alarm rate of 5.3{\%} and a miscue detection rate of 40.1{\%}. These results are worse than current state of the art reading tutors perhaps indicating that dyslexic read speech is a challenge to handle.",
keywords = "l{\ae}sefejlsdetektion, l{\ae}setr{\ae}ner, dysleksi, talegenkendelse, konfidensv{\ae}rdi, miscue detection, reading tutor, dyslexia, speechrecognition, confidence score",
author = "Rasmussen, {Morten H{\o}jfeldt} and Zheng-Hua Tan and B{\o}rge Lindberg and Jensen, {S{\o}ren Holdt}",
year = "2009",
language = "English",
journal = "Proceedings of the International Conference on Spoken Language Processing",
issn = "1990-9772",
publisher = "International Speech Communication Association",

}

A System for Detecting Miscues in Dyslexic Read Speech. / Rasmussen, Morten Højfeldt; Tan, Zheng-Hua; Lindberg, Børge; Jensen, Søren Holdt.

In: Proceedings of the International Conference on Spoken Language Processing, 2009.

Research output: Contribution to journalConference article in JournalResearchpeer-review

TY - GEN

T1 - A System for Detecting Miscues in Dyslexic Read Speech

AU - Rasmussen, Morten Højfeldt

AU - Tan, Zheng-Hua

AU - Lindberg, Børge

AU - Jensen, Søren Holdt

PY - 2009

Y1 - 2009

N2 - While miscue detection in general is a well explored research field little attention has so far been paid to miscue detection in dyslexic read speech. This domain differs substantially from the domains that are commonly researched, as for example dyslexic read speech includes frequent regressions and long pauses between words. A system detecting miscues in dyslexic read speech is presented. It includes an ASR component employing a forced-alignment like grammar adjusted for dyslexic input and uses the GOP score and phone duration to accept or reject the read words. Experimental results show that the system detects miscues at a false alarm rate of 5.3% and a miscue detection rate of 40.1%. These results are worse than current state of the art reading tutors perhaps indicating that dyslexic read speech is a challenge to handle.

AB - While miscue detection in general is a well explored research field little attention has so far been paid to miscue detection in dyslexic read speech. This domain differs substantially from the domains that are commonly researched, as for example dyslexic read speech includes frequent regressions and long pauses between words. A system detecting miscues in dyslexic read speech is presented. It includes an ASR component employing a forced-alignment like grammar adjusted for dyslexic input and uses the GOP score and phone duration to accept or reject the read words. Experimental results show that the system detects miscues at a false alarm rate of 5.3% and a miscue detection rate of 40.1%. These results are worse than current state of the art reading tutors perhaps indicating that dyslexic read speech is a challenge to handle.

KW - læsefejlsdetektion

KW - læsetræner

KW - dysleksi

KW - talegenkendelse

KW - konfidensværdi

KW - miscue detection

KW - reading tutor

KW - dyslexia

KW - speechrecognition

KW - confidence score

M3 - Conference article in Journal

JO - Proceedings of the International Conference on Spoken Language Processing

JF - Proceedings of the International Conference on Spoken Language Processing

SN - 1990-9772

ER -