Application of Deep Neural Network Algorithm in Speech Enhancement of Online English Learning Platform

Haiyan Peng; Min Zhang

doi:10.4108/eetsis.v10i1.2577

Authors

Haiyan Peng Guangzhou Huashang College, Guangzhou, China
Min Zhang Guangzhou Huashang College, Guangzhou, China

DOI:

https://doi.org/10.4108/eetsis.v10i1.2577

Keywords:

deep neural network, online English learning, platform speech, enhancement, denoising, variational modal decomposition

Abstract

INTRODUCTION: In the online English learning platform, noise interference makes people unable to hear the content of English teaching clearly, which leads to a great reduction in the efficiency of English learning. In order to improve the voice quality of online English learning platform, the speech enhancement method of the online English learning platform based on deep neural network is studied.

OBJECTIVES: This paper proposes a deep neural network-based speech enhancement method for online English learning platform in order to obtain more desirable results in the application of speech quality optimization.

METHODS: The optimized VMD (Variable Modal Decomposition) algorithm is combined with the Moth-flame optimization algorithm to find the optimal solution to obtain the optimal value of the decomposition mode number and the penalty factor of the variational modal decomposition algorithm, and then the optimized variational modal decomposition algorithm is used to filter the noise information in the speech signal; Through the network speech enhancement method based on deep neural network learning, the denoised speech signal is taken as the enhancement target to achieve speech enhancement.

RESULTS: The research results show that the method not only has significant denoising ability for speech signal, but also after this method is used, PESQ value of speech quality perception evaluation of speech signal is greater than 4.0dB, the spectral features are prominent, and the speech quality is improved.

CONCLUSION: Through experiments from three perspectives: speech signal denoising, speech quality enhancement and speech spectrum information, the usability of the method in this paper is confirmed.

References

Weisser, A. , Buchholz, J. M. (2019). Conversational speech levels and signal-to-noise ratios in realistic acoustic conditions. Journal of the Acoustical Society of America, 145(1):349-360.

Jamal, N. , Fuad, N . & Sha'Abani, M. (2021) . A Comparative Study of IBM and IRM Target Mask for Supervised Malay Speech Separation from Noisy Background. Procedia Computer Science, 179(4):153-160.

Sivapatham, S., Kar, A. & Ramadoss, R. (2021). Performance analysis of various training targets for improving speech quality and intelligibility. Applied Acoustics, 175(12):107817.

Liu, S., Li, Y. & Fu, W. (2022) Human-centered attention-aware networks for Action recognition, International Journal of Intelligent Systems, online first, doi: 10.1002/int.23029

Sadasivan, J., Dhiman, J. K. & Seelamantula, C. S. (2020). Musical noise suppression using a low-rank and sparse matrix decomposition approach. Speech Communication, 125(2):41-52.

Bayer, F. M., Kozakevicius, A. J. & Cintra, R. J. (2019). An Iterative Wavelet Threshold for Signal Denoising. Signal Processing, 162(SEP.):10-20.

Liu, S., Wang, S., Liu, X., et al. (2022) Human Inertial Thinking Strategy: A Novel Fuzzy Reasoning Mechanism for IoT-Assisted Visual Monitoring, . IEEE Internet of Things Journal, online first, 2022, doi: 10.1109/JIOT.2022.3142115

Demir, O. T., Bjornson, E. (2021). The Bussgang Decomposition of Nonlinear Systems: Basic Theory and MIMO Extensions [Lecture Notes]. IEEE Signal Processing Magazine, 38(1):131-136.

Wakisaka, Y. , Iida, D. & Oshida, H.(2021). Fading Suppression of Φ-OTDR With the New Signal Processing Methodology of Complex Vectors Across Time and Frequency Domains. Journal of Lightwave Technology, 39(13): 4279-4293.

Sedov, E. V., Chekhovskoy, I.S. & Prilepsky, J. E. (2021). Neural network for calculating direct and inverse nonlinear Fourier transform. Quantum Electronics, 51(12):1118-1121.

Li, W. S., Xu, W. J. & Zhang, T. (2021).Improvement of Threshold Denoising Method Based on Wavelet Transform. Computer Simulation, 38(06):348-351,356.

Bo, X. , Zxa, B. & Zw, C.(2020). Gamma spectrum denoising method based on improved wavelet threshold[J]. Nuclear Engineering and Technology, 52( 8):1771-1776.

Zaeni, A. , Kasnalestari, T. & Khayam, U. (2019). Partial discharge signal denoising by using hard threshold and soft threshold methods and wavelet transformation. IOP Conference Series: Materials Science and Engineering, 602(1):012034.

Hameed, A. S. (2021). Speech compression and encryption based on discrete wavelet transform and chaotic signals. Multimedia Tools and Applications, 80(9): 13663-13676.

Barkalov, K., Lebedev, I., & Kozinov, E. (2021).Acceleration of Global Optimization Algorithm by Detecting Local Extrema Based on Machine Learning. Entropy, 23(10): 1272.

Kwasny, D., Hemmerling, D. (2021). Gender and age estimation methods based on speech using deep neural networks. Sensors, 21(14): 4785.

Lü, X., Meng, L. & Chen, C. (2020). Fuzzy Removing Redundancy Restricted Boltzmann Machine: Improving Learning Speed and Classification Accuracy. IEEE Transactions on Fuzzy Systems, 28(10):2495-2509.

Saxena, D., Singh, A. K. (2022). Auto-adaptive learning-based workload forecasting in dynamic cloud environment. International Journal of Computers and Applications, 44(6): 541-551.

Kim, G., Lee, H. & Kim, B. K.(2019). Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition. IEEE signal processing letters, 26(1):159-163.

Jeeva, M., Nagarajan, T. & Vijayalakshmi, P. (2020). Adaptive multi-band filter structure-based far-end speech enhancement. IET Signal Processing, 14(5):288-299.

Liu, S., Xu, X., Zhang, Y., et al. (2022). A Reliable Sample Selection Strategy for Weakly-supervised Visual Tracking, IEEE Transactions on Reliability, online first, doi: 10.1109/TR.2022.3162346