A Comparative Analysis of Various Deep-Learning Models for Noise Suppression
DOI:
https://doi.org/10.4108/eetiot.4502Keywords:
CNN, Noise Suppression, Neural Networks, Audio ProcessingAbstract
Excessive noise in speech communication systems is a major issue affecting various fields, including teleconferencing and hearing aid systems. To tackle this issue, various deep-learning models have been proposed, with autoencoder-based models showing remarkable results. In this paper, we present a comparative analysis of four different deep learning based autoencoder models, namely model ‘alpha’, model ‘beta’, model ‘gamma’, and model ‘delta’ for noise suppression in speech signals. The performance of each model was evaluated using objective metric, mean squared error (MSE). Our experimental results showed that the model ‘alpha’ outperformed the other models, achieving a minimum error of 0.0086 and maximum error of 0.0158. The model ‘gamma’ also performed well, with a minimum error of 0.0169 and maximum error of 0.0216. These findings suggest that the pro-posed models have great potential for enhancing speech communication systems in various fields.
Downloads
References
A. Gupta, A. Gupta, K. Jain, and S. Gupta, “Noise Pollution and Impact on Children Health,” Indian J. Pediatr., vol. 85, no. 4, pp. 300–306, Apr. 2018, doi: 10.1007/s12098-017-2579-7. DOI: https://doi.org/10.1007/s12098-017-2579-7
B. R. C. Molesworth, M. Burgess, and D. Kwon, “The use of noise cancelling headphones to improve concurrent task performance in a noisy environment,” Appl. Acoust., vol. 74, no. 1, pp. 110–115, Jan. 2013, doi: 10.1016/j.apacoust.2012.06.015. DOI: https://doi.org/10.1016/j.apacoust.2012.06.015
R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: an overview and application in radiology,” Insights Imaging, vol. 9, no. 4, pp. 611–629, Aug. 2018, doi: 10.1007/s13244-018-0639-9. DOI: https://doi.org/10.1007/s13244-018-0639-9
D. Suryani, P. Doetsch, and H. Ney, “On the Benefits of Convolutional Neural Network Combinations in Offline Handwriting Recognition,” in 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Oct. 2016, pp. 193–198. doi: 10.1109/ICFHR.2016.0046. DOI: https://doi.org/10.1109/ICFHR.2016.0046
W. Wang, Y. Huang, Y. Wang, and L. Wang, “Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction,” presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014, pp. 490–497. Accessed: Jun. 01, 2023. [Online]. Available: https://www.cv-foundation.org/openaccess/content_cvpr_workshops_2014/W15/html/Wang_Generalized_Autoencoder_A_2014_CVPR_paper.html DOI: https://doi.org/10.1109/CVPRW.2014.79
M. Dogra, S. Borwankar, and J. Domala, “Noise Removal from Audio Using CNN and Denoiser,” in Advances in Speech and Music Technology, vol. 1320, A. Biswas, E. Wennekes, T.-P. Hong, and A. Wieczorkowska, Eds., in Advances in Intelligent Systems and Computing, vol. 1320. , Singapore: Springer Singapore, 2021, pp. 37–48. doi: 10.1007/978-981-33-6881-1_4. DOI: https://doi.org/10.1007/978-981-33-6881-1_4
N. Boyko and А. Hrynyshyn, “Using Recurrent Neural Network to Noise Absorption from Audio Files”.
S. R. Park and J. Lee, “A Fully Convolutional Neural Network for Speech Enhancement.” arXiv, Sep. 22, 2016. Accessed: Apr. 30, 2023. [Online]. Available: http://arxiv.org/abs/1609.07132
S. Sadrizadeh, H. Otroshi-Shahreza, and F. Marvasti, “Impulsive noise removal via a blind CNN enhanced by an iterative post-processing,” Signal Process., vol. 192, p. 108378, Mar. 2022, doi: 10.1016/j.sigpro.2021.108378. DOI: https://doi.org/10.1016/j.sigpro.2021.108378
M. Strake, B. Defraene, K. Fluyt, W. Tirry, and T. Fingscheidt, “Speech enhancement by LSTM-based noise suppression followed by CNN-based speech restoration,” EURASIP J. Adv. Signal Process., vol. 2020, no. 1, p. 49, Dec. 2020, doi: 10.1186/s13634-020-00707-1. DOI: https://doi.org/10.1186/s13634-020-00707-1
H. Zhang and D. Wang, “Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Talk Scenarios,” in Interspeech 2018, ISCA, Sep. 2018, pp. 3239–3243. doi: 10.21437/Interspeech.2018-1484. DOI: https://doi.org/10.21437/Interspeech.2018-1484
R. Ormiston, T. Nguyen, M. Coughlin, R. X. Adhikari, and E. Katsavounidis, “Noise reduction in gravitational-wave data via deep learning,” Phys. Rev. Res., vol. 2, no. 3, p. 033066, Jul. 2020, doi: 10.1103/PhysRevResearch.2.033066. DOI: https://doi.org/10.1103/PhysRevResearch.2.033066
L. Cheng, R. Peng, A. Li, C. Zheng, and X. Li, “Deep learning-based stereophonic acoustic echo suppression without decorrelation,” J. Acoust. Soc. Am., vol. 150, no. 2, pp. 816–829, Aug. 2021, doi: 10.1121/10.0005757. DOI: https://doi.org/10.1121/10.0005757
Y. Ke, A. Li, C. Zheng, R. Peng, and X. Li, “Low-complexity artificial noise suppression methods for deep learning-based speech enhancement algorithms,” EURASIP J. Audio Speech Music Process., vol. 2021, no. 1, p. 17, Apr. 2021, doi: 10.1186/s13636-021-00204-9. DOI: https://doi.org/10.1186/s13636-021-00204-9
W.-H. Lee, M. Ozger, U. Challita, and K. W. Sung, “Noise Learning-Based Denoising Autoencoder,” IEEE Commun. Lett., vol. 25, no. 9, pp. 2983–2987, Sep. 2021, doi: 10.1109/LCOMM.2021.3091800. DOI: https://doi.org/10.1109/LCOMM.2021.3091800
J. Tan, J. Yang, S. Wu, G. Chen, and J. Zhao, “A critical look at the current train/test split in machine learning.” arXiv, Jun. 08, 2021. doi: 10.48550/arXiv.2106.04525.
Ghosh, H., Tusher, M.A., Rahat, I.S., Khasim, S., Mohanty, S.N. (2023). Water Quality Assessment Through Predictive Machine Learning. In: Intelligent Computing and Networking. IC-ICN 2023. Lecture Notes in Networks and Systems, vol 699. Springer, Singapore. https://doi.org/10.1007/978-981-99-3177-4_6 DOI: https://doi.org/10.1007/978-981-99-3177-4_6
Alenezi, F.; Armghan, A.; Mohanty, S.N.; Jhaveri, R.H.; Tiwari, P. Block-Greedy and CNN Based Underwater Image Dehazing for Novel Depth Estimation and Optimal Ambient Light. Water 2021, 13, 3470. https://doi.org/10.3390/w13233470 DOI: https://doi.org/10.3390/w13233470
G. P. Rout and S. N. Mohanty, "A Hybrid Approach for Network Intrusion Detection," 2015 Fifth International Conference on Communication Systems and Network Technologies, Gwalior, India, 2015, pp. 614-617, doi: 10.1109/CSNT.2015.76. DOI: https://doi.org/10.1109/CSNT.2015.76
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 EAI Endorsed Transactions on Internet of Things
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
