THE ADVANTAGE OF INTERPHONEME PROCESSING AT DIPHONE RECOGNITION OF KAZAKH WORDS

Öz

This paper presents a method of interphoneme processing at diphone recognition of Kazakh words. Authors made experiment to test how impact interphoneme processing to recognition accuracy. The experiment results show that recognizable word best differs from the other word on the DTW-Distance after interphoneme processing than without it. The results can be used in the construction of recognition system of single words.

Kaynakça

1. [1] Raut, C.K., Bayesian discriminative adaptation for speech recognition, Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on Eng. Dept., Cambridge Univ., Cambridge , 19-24 April 2009, Page(s): 4361 – 4364
2. [2] Lawrence, R. Rabiner (February 1989). "A tutorial on Hidden Markov Models and selected applications in speech recognition". Proceedings of
3. 3] Al-Alaoui, M.A., Al-Kanj, L., Azar, J., and Yaacoub, E., Speech Recognition using Artificial Neural Networks and Hidden Markov Models, IEEE MULTIDISCIPLINARY ENGINEERING EDUCATION MAGAZINE, VOL. 3, NO. 3, SEPTEMBER 2008
4. [4] Винцюк, Т.К. Анализ, распознавание и интерпретация речевых сигналов. Киев, Наук. думка, 1987.
5. [5] Najkar, N., Razzazi, F., Sameti, H. An evolutionary decoding method for HMMbased continuous speech recognition systems using particle swarm optimizationб Pattern Anal Applic, DOI 10.1007/s10044-012-0313-7
6. [6] Frikha, M., Ben Hamida, A. A Comparitive Survey of ANN and Hybrid HMM/ANN Architectures for Robust Speech Recognition American Journal of Intelligent Systems 2012� 2(1): 1-8 DOI: 10.5923/j.ajis.20120201.01
7. [7] Hosom, J.P., Cole, R., and Fanty, M. Speech Recognition Using Neural Networks at the Center for Spoken Language Understanding. //Center for Spoken Language Understanding, Oregon Graduate Institute of Science and Technology, July 1999.
8. [8] Dev Dhingra, S., Nijhawan, G., Pandit, P., Isolated Digit Recognition Using MFCC AND DTW, International Journal on Advanced Electrical and Electronics Engineering, (IJAEEE), ISSN (Print): 2278-8948, Volume-1, Issue-1, 2012, pp 59-64

9. [9] Шелепов, В.Ю., Ниценко А., Дорохина, Г.В., Карабалаева, М.Х., Бурибаева, А.К. О распознавании речи на основе межфонемных переходов. Вестник. Астана: Евразийский национальный университет им. Л.Н.Гумилева, 2012. – Специальный выпуск.–С.436-440
10. [10]Бурибаева, А.К. Распознавание казахских слов на основе дифонной базы, Труды Международной конференции "Компьютерная обработка тюркских языков" (Turklang- 2013), С. 230-239.