Title |
A Speech Corpus for Dyslexic Reading Training |
Authors |
Jakob Schou Pedersen and Lars Bo Larsen |
Abstract |
Traditional Danish reading training for dyslexic readers typically involves thepresence of a professional reading therapist for guidance, advice andevaluation. Allowing dyslexic readers to train their reading skills on theirown could not only benefit the dyslexics themselves in terms of increasedflexibility but could also allow professional therapists to increase the amountof dyslexic readers to whom they have a professional contact. It is envisionedthat an automated reading training tool operating on the basis of ASR couldprovide dyslexic users with such independence. However, only limited experiencein handling dyslexic input (in Danish) by a speech recognizer exists currently.This paper reports on the establishment of a speech corpus of Danish dyslexicspeech along with an annotation hereof and the setup of a proof-of-concepttraining tool allowing dyslexic users to improve their reading skills on theirown. Despite relatively limited ASR performance, a usability evaluation bydyslexic users shows an unconditional belief in the fairness of the system andindicates furthermore willingness for using such a training tool. |
Language |
Speech Recognition/Understanding |
Topics |
Corpus (creation, annotation, etc.), Speech resource/database, Speech Recognition/Understanding |
Full paper  |
A Speech Corpus for Dyslexic Reading Training |
Bibtex |
@InProceedings{PEDERSEN10.52,
author = {Jakob Schou Pedersen and Lars Bo Larsen}, title = {A Speech Corpus for Dyslexic Reading Training}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |