Automatic analysis of pronunciations for children with speech sound disorders. (July 2018)

• Record Type: Journal Article
• Authors: Dudy, Shiran; Bedrick, Steven; Asgari, Meysam; Kain, Alexander
• Is Part Of: Computer speech & language. Volume 50(2018)
• Page Start: 62
• Page End: 84
• Publication Date: 2018-07
• Subjects: Speech recognition -- Goodness of Pronunciation -- Educational software -- Diagnostic tools -- Speech disorders -- Support Vector Machine; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.12.006
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Propose two approaches for evaluating pronunciations for children with speechsound disorders. GOP-Algorithm – an algorithm based approach. GOP-SVM – a statistical learning based approach. Prove that the proposed approaches outperform the current GOP state-of-the art approach using several different tests. Describe the CCP corpus that contains data of correct and incorrect pronunciations that were essential for the training and testing processes of the proposed methods. Abstract: Computer-Assisted Pronunciation Training (CAPT) systems aim to help a child learn the correct pronunciations of words. However, while there are many online commercial CAPT apps, there is no consensus among Speech Language Therapists (SLPs) or non-professionals about which CAPT systems, if any, work well. The prevailing assumption is that practicing with such programs is less reliable and thus does not provide the feedback necessary to allow children to improve their performance. The most common method for assessing pronunciation performance is the Goodness of Pronunciation (GOP) technique. Our paper proposes two new GOP techniques. We have found that pronunciation models that use explicit knowledge about error pronunciation patterns can lead to more accurate classification whether a phoneme was correctly pronounced or not. We evaluate the proposed pronunciation assessment methods against a baseline state of the art GOP approach, and show that the proposed techniques lead to classification performance that is more similar to that of a human expert.