论文信息 - COMPUTER BASED ENGLISH SPEAKING TEST BASED ON ARTIFICAL NEURAL NETWORK

COMPUTER BASED ENGLISH SPEAKING TEST BASED ON ARTIFICAL NEURAL NETWORK

English testing is a most common test conducted around the world for evaluating an individual’s English capabilities in mostly reading, writing, speaking, and listening domain. With increased cost and higher subjective assessment attached in some tests, there is required to change the test from traditional method to computer based. In this study, a proposed method for conducting speaking test for English based on objective assessment method. The proposed system is able to identify different dialects based on unit analysis of syllable along with phonetic errors. The proposed system is based on pronunciation parameters and neural network for evaluation purpose. The PSO algorithm is used for training the artificial neural network. The experiment result conducted for validating the proposed system shows promising performance

Yu Min | Xin Wang | Chao Li

[1] Tirtharaj Dash,et al. English Character Recognition using Artificial Neural Network , 2013, ArXiv.

[2] M. Teshnehlab,et al. Training ANFIS structure with modified PSO algorithm , 2007, 2007 Mediterranean Conference on Control & Automation.

[3] Martin T. Hagan,et al. Neural network design , 1995 .

[4] A. Gray,et al. Distance measures for speech processing , 1976 .

[5] Kaushik Deb,et al. N EURAL N ETWORK -BASED ENGLISH ALPHANUMERIC CHARACTER RECOGNITION , 2012 .

[6] Robert E. Yantorno,et al. Performance of the modified Bark spectral distortion as an objective speech quality measure , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[7] I. Elamvazuthi,et al. Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques , 2010, ArXiv.