Abstract

This study aims to develop a computerized technique that uses speech recognition as a helping tool in speech therapy diagnosis for early detection. Somehow speech disorder can be divided into few categories which not all type will be fully covered in this research. This study only purposes a solving method for diagnosis of a patient that suffers from articulation disorder. Therefore a set of Malay language vocabulary has already been designed to tackle this issue where it will cover selected Malay consonants as a target words. Ten Malay target words had been choose to test the recognition accuracy of this system and the sample are taken from real patient from Hospital Sultanah Aminah (HSA: Speech therapist at Speech Therapy Center) where the hospital assists in the clinical trial. The result accuracy of the systems will help the Speech Therapist (ST) to give an early diagnosis analysis for the patient before next step can be purposed. An early percentage of correct sample achieved almost 50% in this experiment.

Keywords:

Feature extraction technique, Hidden Markov Model (HMM), segmentation, speech articulation disorder, speech recognition, speech therapy,

References

1. Axelsson, A. and E. Björhall, 2003. Real time speech driven face animation. M.S. Thesis, the Image Coding Group, Department of Electrical Engineering, Linköping University, Linköping.
   
2. Chen, B., 1998. Search Algorithms for Speech Recognition (PowerPoint Slides).
   Direct Link
3. Davis, S. and P. Mermelsten, 1980. Comparison of parametric representation for monosyllabic word recognition in continuous spoken sentence. IEEE T. Acoust. Speech, 28: 357-366.
   CrossRef    
4. Ellis, D. and N. Morgan, 1999. Size matters: An empirical study of neural network training for large vocabulary continuous speech recognition. Proceeding of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2: 1013-1016.
   CrossRef    
5. Juang, B.H., 1985. Hidden Markov Models. Encyclopedia of Telecommunications.
   PMid:18553591    
6. Kumar, S. and P. Mallikarjuna Rao, 2011. Design of an automatic speaker recognition system using MFCC, vector quantization and LBG algorithm. Int. J. Comput. Sci. Eng., 3: 2942-2954.
   
7. Ooi, C.A. and J. Yunus, 2007. Computer-based system to assess efficacy of stuttering therapy techniques. Proceeding of the International Conference on Biomedical Engineering, 15: 374-377.
   
8. Powers, M.H., 1971. Clinical Educational Procedures in Functional Disorders of Articulation. In: Travis, L.E. (Ed.), Handbook of Speech Pathology and Audiology. Prentice-Hall, Englewood Cliffs, N.J.
   
9. Riper Van, C., 2007. Personal Correspondence to Wayne Secord. In: Secord et al. (Eds.), 2nd Edn., Eliciting Sounds: Techniques and Strategies for Clinicians. Thomas Delmar Learning, Clifton Park, NY, pp: 8.
   
10. Saz, O., S.C. Yin, E. Lleida, R. Rose, C. Vaquero and W.R. Rodríguez, 2009. Tools and technologies for computer-aided speech and language therapy. J. Speech Commun., 51(10): 948-967.
    CrossRef    
11. Tan, T.S. and H.S.S. Sheikh, 2008. Corpus-based Malay text-to-speech synthesis system. Proceeding of the 14th Asia-Pacific Conference on Communications (APCC, 2008). Tokyo, Oct. 14-16, pp: 1-5.
    
12. Tan, T.S., A.K. Ariff, C.M. Ting and S.H. Salleh, 2007. Application of Malay speech technology in Malay speech therapy assistance tools. Proceeding of the IEEE International Conference on Intelligent and Advanced Systems (ICIAS '07), Nov. 25-28, pp: 330-334.
    CrossRef    
13. Ting, H.N., J. Yunus, S. Vandort and L.C. Wong, 2003. Computer-based Malay articulation training for Malay plosives at isolated, syllable and word level. Proceeding of the International Conference on Information, Communications and Signal Processing, 3: 1423-1426.
    CrossRef    
14. Ting, C.M., S.H. Salleh, T.S. Tan and A.K. Ariff, 2007. Automatic phonetic segmentation of Malay speech database. Proceeding of the IEEE 6th International Conference on Information, Communications and Signal Processing, pp: 1-4.
    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.