| Literature DB >> 9328878 |
Abstract
This program of work is intended to develop automatic recognition procedures to locate and assess stuttered dysfluencies. This and the following article together, develop and test recognizers for repetitions and prolongations. 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 that are segmented are words. Here assessments by human judges on the speech of 12 children who stutter are described using a corresponding procedure. The accuracy of word boundary placement across judges, categorization of the words as fluent, repetition or prolongation, and duration of the different fluency categories are reported. These measures allow reliable instances of repetitions and prolongations to be selected for training and assessing the recognizers in the subsequent paper.Entities:
Mesh:
Year: 1997 PMID: 9328878 PMCID: PMC2000472 DOI: 10.1044/jslhr.4005.1073
Source DB: PubMed Journal: J Speech Lang Hear Res ISSN: 1092-4388 Impact factor: 2.297