Abstract
The main aim of this work is to develop and test the system that would automatically assess correctness of articulation of <r> consonant in child speech. The system should contain automatic speech recognition module and classification module. As there are many solutions connected with speech analysis with heavy load of algorithms based on complicated mathematical and statistical operations, motivation was to exchange them with simpler, but quite powerful softcomputing methods. The major assumption is to develop system, that would fulfill following requirements: speaker independence, recording device independence, high performance - immediate response, high accuracy. MLP used as classifier recognized properly more than 89% of sound probes. The systems is created for Polish language.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
American Speech-Language-Hearing Association, Speech sound disorders. https://www.asha.org/public/speech/disorders/SSDcauses.htm. Accessed 21 Mar 2018
Audacity Team, Audacity, Free, open source, cross-platform software for recording and editing sounds. http://audacity.sourceforge.net/. Accessed 08 Mar 2018
Bowen, C.: Ages and stages summary. http://www.speech-language-therapy.com. Accessed 08 Feb 2018
Hosom, J.P., Shriberg, L., Green, J.R.: Diagnostic assessment of childhood apraxia of speech using automatic speech recognition (ASR) methods. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1622919/. Accessed 13 Mar 2018
Su, H.-Y., Wu, C.-H., Tsai, P.-J.: Automatic assessment of articulation disorders using confident unit-based model adaptation. http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=4518659&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D4518659. Accessed 12 Mar 2018
Maheswari, N., Kabilan, A.P., Venkatesh, R.: Speaker independent phoneme recognition using neural networks. http://www.jatit.org/volumes/research-papers/Vol6No2/12Vol6No2.pdf. Accessed 20 Feb 2018
Matsumasa, H., Takiguchi, T., Ariki, Y.: PCA-based feature extraction for fluctuation in speaking style of articulation disorders. http://www.me.cs.scitec.kobe-u.ac.jp/publications/papers/2007/IS070653.pdf. Accessed 21 Feb 2018
Polish Phonetic Association, Speech and language technology, reports and technical notes. http://ptfon.pl/en/slt. Accessed 11 Mar 2018
Prica, B., Ilic, S.: Recognition of vowels in continuous speech by using formants. http://facta.junis.ni.ac.rs/eae/fu2k103/11prica.pdf. Accessed 11 Mar 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Mazurkiewicz, J. (2019). System for Child Speech Problems Identification. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds) Contemporary Complex Systems and Their Dependability. DepCoS-RELCOMEX 2018. Advances in Intelligent Systems and Computing, vol 761. Springer, Cham. https://doi.org/10.1007/978-3-319-91446-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-91446-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91445-9
Online ISBN: 978-3-319-91446-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)