Development of a Two-Stage Procedure for the Automatic Recognition of Dysfluencies in the Speech of Children Who Stutter II. ANN Recognition of Repetitions and Prolongations With Supplied Word Segment Markers Research Article
Research Article  |   October 01, 1997
Development of a Two-Stage Procedure for the Automatic Recognition of Dysfluencies in the Speech of Children Who Stutter
 
Author Affiliations & Notes
  • Peter Howell
    University College London England
  • Stevie Sackin
    University College London England
  • Kazan Glenn
    University College London England
Article Information
Speech, Voice & Prosodic Disorders / Fluency Disorders / Speech / Research Articles
Research Article   |   October 01, 1997
Development of a Two-Stage Procedure for the Automatic Recognition of Dysfluencies in the Speech of Children Who Stutter
Journal of Speech, Language, and Hearing Research, October 1997, Vol. 40, 1085-1096. doi:10.1044/jslhr.4005.1085
History: Received August 8, 1996 , Accepted February 24, 1997
 
Journal of Speech, Language, and Hearing Research, October 1997, Vol. 40, 1085-1096. doi:10.1044/jslhr.4005.1085
History: Received August 8, 1996; Accepted February 24, 1997

This program of work is intended to develop automatic recognition procedures to locate and assess stuttered dysfluencies. This and the preceding article focus on developing and testing recognizers for repetitions and prolongations in stuttered speech. The automatic recognizers classify the speech in two stages: In the first the speech is segmented and in the second the segments are categorized. The units segmented are words. The current article describes results for an automatic recognizer intended to classify words as fluent or containing a repetition or prolongation in a text read by children who stutter that contained the three types of words alone. Word segmentations are supplied and the classifier is an artificial neural network (ANN). Classification performance was assessed on material that was not used for training. Correct performance occurred when the ANN placed a word into the same category as the human judge whose material was used to train the ANNs. The best ANN correctly classified 95% of fluent, and 78% of dysfluent words in the test material.

Acknowledgments
This research was supported by a grant from the Wellcome Trust. Grateful thanks to the children, their parents, and the staff of the Michael Palin Centre for Stammering Children (particularly Lena Rustin and Frances Cook). The comments of Drs. Au-Yeung, Curlee, Colcord, and Jennifer B. Watson are gratefully acknowledged.
Order a Subscription
Pay Per View
Entire Journal of Speech, Language, and Hearing Research content & archive
24-hour access
This Article
24-hour access