Выходит 12 номеров в год
ISSN Печать: 0040-2508
ISSN Онлайн: 1943-6009
Indexed in
SPEECH RECOGNITION OPTIMIZATION OF INTERACTIVE SPOKEN ENGLISH INSTRUCTIONS
Get access
Краткое описание
With the rapid development of science and technology, speech recognition has become a new and main form of human-computer interaction, and English as an international language connects the humanistic economic exchanges around the world, which has important significance to the optimization study of the speech recognition system for spoken English instructions. In this study, the preprocessing of speech signals was explained firstly, and then a characteristic parameter based on the Gammatone filter which simulates cochlea and index compression was introduced. Back Propagation (BP) learning algorithm was applied to control the process of speech feature parameter recognition. Finally, a simulation experiment was carried out on the proposed algorithm using MATLAB software, an English speech corpus was established, and the algorithm was compared with speech recognition algorithms based on Mel-frequency cepstral coefficient and BP neural network. The simulation experiment suggested that the accuracy rate of speech recognition of the proposed algorithm was higher than speech recognition algorithm based on Mel-frequency cepstral coefficient; in the recognition of sentences comprising of the same number of words, the average recognition rate of the proposed algorithm was 3% higher; when Signal to Noise Ratio (SNR) was between 15 dB and 30 dB, the average recognition rate of the algorithm based on GFECC was higher than the algorithm based on MFCC. Hence the proposed algorithm has stronger anti-noise robustness and higher accuracy in speed recognition and can be applied in a noisy speed recognition environment, in reality, to help learners involve in speech recognition based interactive spoken English learning.
-
Li, J., Deng, L., Haeb-Umbach, R., et al., (2016) Chapter 2 - Fundamentals of speech recognition, Robust. Autom. Speech Recogn., pp. 9-40.
-
Doremalen, J.V., Lou, B., Colpaert, J., et al., (2016) Evaluating automatic speech recognition-based language learning systems: a case study, Comput. Assist. Lang. L., 29(4), pp. 1-19.
-
Boves, P.D.L.W.J., (2014) Developing automatic speech recognition-enabled language learning applications: From theory to practice, Anal. Chem., 32(9), pp. 1093-1098.
-
Deng, L., Hinton, G., and Kingsbury, B., (2013) New types of deep neural network learning for speech recognition and related applications: an overview, IEEE Int. Conf. Acoust. Speech Signal Process., pp. 8599-8603.
-
Calderon, J.F., (2011) Face-to-face collaborative learning supported by mobile phones, Interact. Learn. Envir., 19(4), pp. 351-363.
-
Crews, T., Biswas, G., Goldman, S., et al., (2011) Anchored Interactive Learning Environments, Int. J. Ai. Educ., 8, pp. 142-178.
-
Maher, R., Millar, D.S., Savory, S.J., et al., (2012) SOA blanking and signal pre-emphasis for wavelength agile 100Gb/s transmitters, Opto-Electron. Commun. Conf., pp. 905-906.
-
Cao, C.F., Liang, H.R., and Liang, G.C., (2014) Research on Information Technology with Voiceprint Authentication Algorithm and its Implementation on Mobile Terminal, Adv. Mater. Res., 886, pp. 698-701.
-
Zeng, X. and Wang, S., (2014) Underwater sound classification based on Gammatone filter bank and Hilbert-Huang transform, IEEE Int. Conf. Signal Process. Commun. Comput., pp. 707-710.
-
Wahls, S. and Poor, H.V., (2013) Introducing the fast nonlinear Fourier transform, IEEE Int. Conf. Acoust. Speech Signal Process., pp. 5780-5784.
-
Li, J. and Wang, J.P., (2011) Some results of the range about the exponential Radon transform, Boundary Value Problems, Integral Equations and Related Problems, Singapore: World Scientific Publishing Co., pp. 392-398.
-
Babu, M., Arun, K.M.N., and Santhosh, M.S.M., (2014) Extracting MFCC and GTCC features for emotion recognition from audio speech signals, Int. J. Res. Comput. Appl. Robot., 2(8), pp. 46-63.
-
Lin, Y.J. and Chen, X.J., (2014) BP Neural Network Learning Algorithm and its Software Implementation, Appl. Mech. Mater., 513-517, pp. 738-741.
-
Chen, X. and Tang, J., (2014) Application of Improved BP Neural Network in the Frequency Identification of Piano Tone, Lect. Notes Electr. Eng., 277, pp. 243-251.