Abstract
In this paper, a method is proposed to enhance the Signal to Noise Ratio (SNR) of speech by combining the wavelet algorithm with deep learning techniques. First, wavelet threshold denoising is introduced for speech enhancement. Second, the deep neural network is proposed to enhance SNR with Ideal Binary Mask. To achieve a better performance, the speech signal is analyzed with these methods with characteristic parameters. Third, these methods compose a novel method to refine the process of speech enhancement. Design efficiency and effectiveness are compared analytically and computationally via numerical experiments, which justifies the superiority of this combination method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kandagatla, R., Subbaiah, P.V.: Speech enhancement using MMSE estimation under phase uncertainty. Int. J. Speech Technol. 20(2), 373–385 (2017)
Abou-loukh, S.J., Ibrahim, A.K.: Speech denoising using mixed transform. 16(1) (2017)
Seke, E., Özkan, K.: A new speech signal denoising algorithm using common vector approach. Int. J. Speech Technol. 21, 659–670 (2018)
Yanlei, Z., Shifeng, O., Ying, G.: Improved wiener filter algorithm for speech enhancement. Autom. Control Intell. Syst. 7(3), 92–98 (2019)
Cornell, S., et al.: A novel adversarial training scheme for deep neural network based speech enhancement. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2020)
Wei, L., Li, W.: A Speech denoising method Based on wavelet threshold and improved spectral subtraction. In: IICCSEE-13 (2013)
Swami, P.D., Sharma, R., Jain, A., Swami, D.K.: Speech enhancement by noise driven adaptation of perceptual scales and thresholds of continuous wavelet transform coefficients. Speech Commun. 70, 1–12 (2015)
Jia, H.R., Zhang, X.Y., Bai, J.: A continuous differentiable wavelet threshold function for speech enhancement. J. Central South Univ. 20(8), 2219–2225 (2013)
Erdmann, M., Martin, E., Jonas, G.: Deep learning based algorithms in astroparticle physics. In: Journal of Physics: Conference Series, vol. 1525, no. 1 (2020)
Liu, D., Smaragdis, P., Kim, M.: Experiments on deep learning for speech denoising. In: Interspeech (2014)
Xia, W., Wu, Q., Feng, X.: Research on speech accurate recognition technology based on deep learning DNN-HMM. In: International Symposium on Multispectral Image Processing and Pattern Recognition (2020)
Nossier, S.A., Wall, J., Moniri, M., Glackin, C., Cannings, N.: An experimental analysis of deep learning architectures for supervised speech enhancement. Electronics 10(1), 17 (2020)
Fuzzy Research; Study Results from Inner Mongolia University for the Nationalities Broaden Understanding of Fuzzy Research (Multimedia english teaching analysis based on deep learning speech enhancement algorithm and robust expression positioning). Rob. Mach. Learn. 715 (2020)
Wang, L., Zheng, W., Ma, X., Lin, S.: Denoising speech based on deep learning and wavelet decomposition. Sci. Program. 2021, 1–10 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yue, L., Ji, Q. (2024). Speech Enhancement Based on the Combination of Deep Learning and Wavelet Algorithm. In: El Fadil, H., Zhang, W. (eds) Automatic Control and Emerging Technologies. ACET 2023. Lecture Notes in Electrical Engineering, vol 1141. Springer, Singapore. https://doi.org/10.1007/978-981-97-0126-1_16
Download citation
DOI: https://doi.org/10.1007/978-981-97-0126-1_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0125-4
Online ISBN: 978-981-97-0126-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)