Sibilant consonants classification comparison with multi‐ and single‐class neural networks. Issue 6 (9th September 2020)

• Record Type: Journal Article
• Authors: Anjos, Ivo; Cavalheiro Marques, Nuno; Grilo, Margarida; Guimarães, Isabel; Magalhães, João; Cavaco, Sofia
• Other Names: Gonzalez‐Pardo Antonio guestEditor.; Tallón‐Ballesteros Antonio J. guestEditor.; Yin Hujun guestEditor.; Cortez Paulo guestEditor.; Bifet Albert guestEditor.
• Is Part Of: Expert systems. Volume 37:Issue 6(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-09-09
• Subjects: deep learning -- machine learning -- neural networks -- sibilant consonants -- speech and language therapy; Expert systems (Computer science); 006.33
• DOI: 10.1111/exsy.12620
• Languages: English
• ISSNs: 0266-4720

Abstract

Abstract: Many children with speech sound disorders cannot pronounce the sibilant consonants correctly. We have developed a serious game, which is controlled by the children's voices in real time, with the purpose of helping children on practicing the production of European Portuguese (EP) sibilant consonants. For this, the game uses a sibilant consonant classifier. Since the game does not require any type of adult supervision, children can practice producing these sounds more often, which may lead to faster improvements of their speech. Recently, the use of deep neural networks has given considerable improvements in the classification of a variety of use cases, from image classification to speech and language processing. Here, we propose to use deep convolutional neural networks to classify sibilant phonemes of EP in our serious game for speech and language therapy. We compared the performance of several different artificial neural networks that used Mel frequency cepstral coefficients or log Mel filterbanks. Our best deep learning model achieves classification scores of 95.48% using a 2D convolutional model with log Mel filterbanks as input features. Such results are then further improved for specific classes with simple binary classifiers.