Howell P, Sackin S, Glenn K
Department of Psychology, University College London, England.
J Speech Lang Hear Res. 1997 Oct;40(5):1073-84. doi: 10.1044/jslhr.4005.1073.
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.
本工作计划旨在开发自动识别程序,以定位和评估口吃性言语不流畅。本文与后续文章一起,开发并测试重复和延长的识别器。自动识别器分两个阶段对语音进行分类:第一阶段,对语音进行分段;第二阶段,对各片段进行分类。分段的单位是单词。本文描述了人类评判员使用相应程序对12名口吃儿童的语音进行的评估。报告了不同评判员在单词边界划分上的准确性、单词被分类为流畅、重复或延长的情况,以及不同流畅性类别的时长。这些测量结果使得能够选择可靠的重复和延长实例,用于后续论文中训练和评估识别器。