ALGORITHM FOR PHONOGRAM COMPARISON IN E-LEARNING SYSTEMS
Abstract
An algorithm for determination of the degree of phonogram matching on the basis of linear spectral frequency and dynamic time warping is considered. The problem of phonogram comparison is handled as the problem of recognizing the analyzed speech signal, which contains a lot of distortion and noise with unknown beginning and duration, non-linear timescale, and unknown pronunciation sample. A functional diagram of the algorithm is presented.
About the Authors
V. V. Kiselev
ООО «Речевые технологии»
Russian Federation
Russian Federation
A. G. Davydau
ООО «Речевые технологии»
Russian Federation
Russian Federation
A. A. Tkachenia
ООО «Речевые технологии»
Russian Federation
Russian Federation
References
1. Stanley, T. Improving L1-specific phonological error diagnosis in computer assisted pronunciation training / T. Stanley, K. Hacioglu // Proc. of Interspeech. – Portland, Oregon, 2012. – P. 153–159.
2. Rose, R. Verifying session level pronunciation accuracy in a speech therapy application /R. Rose, S.-C. Yin, Y. Tang // Proc. of Interspeech. – Portland, Oregon, 2012. – P. 267–272.
3. Perceived speech quality estimation using DTW algorithm / I. Kraljevski [et al.] // Telfor Journal. – 2009. – № 1. – P. 25–31.
4. Performance of DTW speech recognizer on packet switched network / I. Kraljevski [et al.] //Proc. of 7th ETAI Conf. – Ohrid, Macedonia, 2005. – P. 89–96.
5. Paliwal, K.K. On the use of line spectral frequency parameters for speech recognition /K.K. Paliwal // Proc. of Digital. Signal Processing 2. – Bombay, India, 1992. – P. 80–87.
6. Sakhnov, K. Approach for energy-based voice detector with adaptive scaling factor /K. Sakhnov, E. Verteletskaya, B. Simak // IAENG Intern. Journal of Computer Science. – 2009. –№ 36 (4). – P. 48–53.
7. Kabal, P. The computation of line spectral frequencies using chebyshev polynomials /P. Kabal, R.P. Ramachandran // IEEE Trans. Acoustics, Speech, Signal Processing. – 1986. –№ 34 (6). – P. 1419–1426.
8. Rabiner, L. Fundamentals of speech recognition / L. Rabiner, B.-H. Juang. – NJ, USA,1993. – 496 p.
9. Keogh, E. Exact indexing of dynamic time warping / E. Keogh, C.A. Ratanamahatana. –USA : University of California–Riverside, 2004. – 417 p.
10. Профессор Хиггинс. Русский без акцента! // ИстраСофт [Электронный ресурс]. –Режим доступа : http://www.istrasoft.ru/ru/programmy/professor-higgins-russkij-bez-akcenta.html. –Дата доступа : 11.09.2013.
Review
For citations:
Kiselev V.V., Davydau A.G., Tkachenia A.A. ALGORITHM FOR PHONOGRAM COMPARISON IN E-LEARNING SYSTEMS. Informatics. 2013;(4):30-35. (In Russ.)
Views: 852
Email this article 