Automatic detection of articulation disorders in children with cleft lip and palate

Abstract

Speech of children with cleft lip and palate (CLP) is sometimes still disordered even after adequate surgical and nonsurgical therapies. Such speech shows complex articulation disorders, which are usually assessed perceptually, consuming time and manpower. Hence, there is a need for an easy to apply and reliable automatic method. To create a reference for an automatic system, speech data of 58 children with CLP were assessed perceptually by experienced speech therapists for characteristic phonetic disorders at the phoneme level. The first part of the article aims to detect such characteristics by a semiautomatic procedure and the second to evaluate a fully automatic, thus simple, procedure. The methods are based on a combination of speech processing algorithms. The semiautomatic method achieves moderate to good agreement (kappa approximately 0.6) for the detection of all phonetic disorders. On a speaker level, significant correlations between the perceptual evaluation and the automatic system of 0.89 are obtained. The fully automatic system yields a correlation on the speaker level of 0.81 to the perceptual evaluation. This correlation is in the range of the inter-rater correlation of the listeners. The automatic speech evaluation is able to detect phonetic disorders at an experts'level without any additional human postprocessing.

PEAKS – A system for the automatic evaluation of voice and speech disorders

“…The assessment result would then be more detailed, i.e., the reduction in intelligibility could then be related to the kind of the disorder. First results are presented in Maier et al (2008).…”

Toward clinical application of landmark-based speech analysis: Landmark expression in normal adult speech

“…This requires considerable time and labor, making such tools impractical for busy clinicians. Many authors have put substantial research effort in to automate the analysis for clinical assessment of disordered speech (Berisha et al, 2013;Bocklet et al, 2012;He et al, 2013;Lustyk et al, 2014;Maier et al, 2009;Middag et al, 2009;Zhou et al, 2012). Landmark (LM) analysis is a novel approach that characterizes speech with acoustic markers that are developed based on the LM theory of speech perception.…”

Speech Production Quality of Cochlear Implant Users with Respect to Duration and Onset of Hearing Loss

“…In previous investigations, ASR analysis and perceptually evaluated speech intelligibility showed agreement between 0.84 and 0.94 using Spearman rank correlation. The technique even allows for some more detailed analysis of altered speech: next to intelligibility assessment, even distinct alterations of phonetic features and of nasality in comparison to normal speech can be detected [38]. …”