Email this article 
Open Access
Subscription or Fee Access
Intelligent Deep Learning Based Speech Receivers
(*) Corresponding author
DOI: https://doi.org/10.15866/irecap.v13i4.23715
Abstract
This paper discusses the design, training, and comparison of various neural networks for creating a Deep Learning (DL)-based alternative to the conventional digital communication speech receiver for baseband demodulation. The models under consideration include Long Short-Term Memory (LSTM), 1-dimensional convolutional neural networks (Conv1D), and 2-dimensional convolutional neural networks (Conv2D). These models are robust enough for the reliable recovery of a practical A-law algorithm-based PCM-encoded speech signal done using a Spartan 6 mini Field Programmable Gate Array (FPGA) board, which is then bipolarly signaled and sent over an Additive White Gaussian Noise (AWGN) communication channel. Various time domain statistics of the speech signal, like Short-Term Energy (STE), Zero Crossing Rate (ZCR), autocorrelation, and Bit Error Rate (BER), are measured and compared with those of a conventional receiver subjected to noise with a Signal-to-Noise Ratio (SNR) in the range of -50 dB to 20 dB. The simulation results show better performance of the DL model, which promises reduced computational and hardware complexities in the future of signal detection in communication systems.
Copyright © 2023 Praise Worthy Prize - All rights reserved.
Keywords
References
Yang, Janice H and Goodman, Emmett D and Dawes,et .al, Using AI and computer vision to analyze technical proficiency in robotic surgery, Surgical Endoscopy, pp.3010--3017, Volume: 37, Springer (2023).
https://doi.org/10.1007/s00464-022-09781-y
Doncieux, Stephane and Chatila, Raja and Straube, Sirko and Kirchner, Frank, Human-centered AI and robotics, pp:1-14, Volume: 4, SpringerOpen (2022).
https://doi.org/10.1186/s42467-021-00014-x
Hosseini, Mohammad and Rasmussen, Lisa M and Resnik, David B, Using AI to write scholarly publications, Accountability in research, pp:1-9, Taylor & Francis, (2023).
https://doi.org/10.1080/08989621.2023.2168535
Altaheri, Hamdi and Muhammad, Ghulam and Alsulaiman, Mansour and Amin and et. al, Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: A review, Neural Computing and Applications, pp: 14681-14722, Volume 35 (2023), Springer.
https://doi.org/10.1007/s00521-021-06352-5
H. Zhou, L. Jiao, S. Zheng, L. Yang, W. Shen, X. Yang, Generative adversarial network-based electromagnetic signal classification: A semi-supervised learning framework, China Communication, volume 17, pp: 157-169, (2020).
https://doi.org/10.23919/JCC.2020.10.011
Dai, Jincheng and Wang, Sixian and Tan, Nonlinear transform source-channel coding for semantic communications, IEEE Journal on Selected Areas in Communications, pp: 2300-16, Volume: 40.
https://doi.org/10.1109/JSAC.2022.3180802
Bourtsoulatze, Eirina and Kurka, David Burth and Deniz, Deep joint source-channel coding for wireless image transmission, IEEE Transactions on Cognitive Communications and Networking, pp: 567-579, (2021).
https://doi.org/10.1109/TCCN.2019.2919300
Unnisa, Nazeer and Tatineni, Madhavi, Adaptive deep learning strategy with red deer algorithm for sparse channel estimation and hybrid precoding in millimeter wave massive MIMO-OFDM systems,Wireless Personal Communications, volume 122, Springer (2022).
https://doi.org/10.1007/s11277-021-09039-1
Kapula, Prabhakara Rao and Sridevi, PV, Channel estimation in 5G multi input multi output wireless communication using optimized deep neural framework, Cluster Computing, Volume:25, pp:3517-30, Springer (2022).
https://doi.org/10.1007/s10586-022-03587-2
Shrestha, Ajay and Mahmood, Ausif, Review of deep learning algorithms and architectures, IEEE Access, pp. 53040-53065, Volume: 7, (2019).
https://doi.org/10.1109/ACCESS.2019.2912200
Huang, Hongji and Guo, et al., Deep learning for physical-layer 5G wireless techniques: Opportunities, challenges and solutions, IEEE Wireless Communications, pp. 214--222, Volume 27, (2019).
https://doi.org/10.1109/MWC.2019.1900027
Bahar Azari and Hai Cheng and Nasim Soltani and Haoqing Li, Automated deep learning-based wide-band receiver, Computer Networks, Volume 218, 2022.
https://doi.org/10.1016/j.comnet.2022.109367
T. O'Shea, J. Hoydis, An Introduction to Deep Learning for the Physical Layer, IEEE Transactions on Cognitive Communications and Networking, pp. 1-1 (2017).
H. Zhang, L. Zhang, Y. Jiang, 11th International Conference on Wireless Communications and Signal Processing (WCSP), IEEE, pp. 1-6(2019).
S. Zheng, S. Chen, X. Yang, DeepReceiver: A deep learning-based intelligent receiver for wireless communications in the physical layer, IEEE Transactions on Cognitive Communications and Networking ,Volume:7, pp:5-20 (2020).
https://doi.org/10.1109/TCCN.2020.3018736
M. Honkala, D. Korpi, J.M.J. Huttunen, DeepRx: Fully convolutional deep learning receiver, pp:3925--3940, IEEE Transactions on Wireless Communications, IEEE, Volume 20 (2021).
https://doi.org/10.1109/TWC.2021.3054520
B. Wang, K. Xu, P. Song, Y. Zhang, Y. Liu, Y. Sun, A Deep Learning-Based Intelligent Receiver for OFDM, IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems(MASS), pp. 562-563, IEEE, 2021.
https://doi.org/10.1109/MASS52906.2021.00075
B. Wang, K. Xu, S. Zheng, H. Zhou, Y. Liu, A deep learning-based intelligent receiver for improving the reliability of the MIMO wireless communication system, IEEE Transactions on Reliability (2022), pp.1104--1115, Vol 71.
https://doi.org/10.1109/TR.2022.3148114
E. V. Rogozhnikov, K. V. Savenko, A. K. Movchan, E.M. Dmitriyev, The study of correlation receivers, International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM), pp. 155-159, IEEE, 2019.
https://doi.org/10.1109/EDM.2019.8823315
T. Wu, CNN and RNN-based deep learning methods for digital signal demodulation, International Conference on Image, Video and Signal Processing- IVSP, pp. 122--127, 2019.
https://doi.org/10.1145/3317640.3317656
J.C. Bellamy, Digital telephony(A Wiley-Interscience Publication. Texas, USA, 1990).
B. Sklar, et al., Digital communications, Vol. 2 (Prentice hall Upper Saddle River, NJ, USA:, 2001).
S. Haykin, Digital communications (Wiley New York, 1988).
N. Farsad, A. Goldsmith, Neural network detection of data sequences in communication systems, IEEE Transactions on Signal Processing, Volume: 66, (2018).
https://doi.org/10.1109/TSP.2018.2868322
Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert, Multilayer feedforward networks are universal approximators, Neural networks, Volume:2, pp 359-366, (1989).
https://doi.org/10.1016/0893-6080(89)90020-8
Varsha PS and Hari VS, LSTM based Receiver Design for Baseband Signal Demodulation, IEEE International Conference on Computing, Communication, and Intelligent Systems, pp. 713-718, 2022.
https://doi.org/10.1109/ICCCIS56430.2022.10037633
A. Sherstinsky, Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network, Physica D: Nonlinear Phenomena ,volume 404, (2020).
https://doi.org/10.1016/j.physd.2019.132306
A.M. Ahmad, S. Ismail, D. Samaon,Recurrent neural network with backpropagation through time for speech recognition, IEEE International Symposium on Communications and Information Technology, .,vol. 1, pp. 98-102,2004.
R. Yamashita, M. Nishio, R.K.G. Do, K. Togashi, Convolutional neural networks: an overview and application in radiology, Insights into imaging, volume 9, (2018).
https://doi.org/10.1007/s13244-018-0639-9
Bachu, R., Kopparthi, S., Adapa, B., Barkana, B. (2010). Voiced/Unvoiced Decision for Speech Signals Based on Zero-Crossing Rate and Energy. In: Elleithy, K. (eds) Advanced Techniques in Computing Sciences and Software Engineering. Springer, Dordrecht.
https://doi.org/10.1007/978-90-481-3660-5_47
M. Jalil, F.A. Butt, A. Malik, Short-time energy, magnitude, zero crossing rate and autocorrelation measurement for discriminating voiced and unvoiced segments of speech signals, The international conference on technological advances in electrical, electronics and computer engineering (TAEECE), IEEE, pp. 208-212, (2018).
Cheng, Siyi and Wang, Chao and Yue, Keqiang and Li, Ruixue and Shen, Automated sleep apnea detection in snoring signal using long short-term memory neural networks, Biomedical Signal Processing and Control, Elsevier, Volume 71,(2022).
https://doi.org/10.1016/j.bspc.2021.103238
K. R. Godfrey, Correlation method, Automatica, Volume 16, Elsevier(1980).
https://doi.org/10.1016/0005-1098(80)90076-X
R. Kumar, R. Arora, V. Bansal, V.J. Sahaya Sheela, H. Buckchash, J. Imran, N. Narayanan, G.N. Pandian, B. Raman, Classification of COVID-19 from chest x-ray images using deep features and correlation coefficient, Multimedia Tools and Applications, Volume:81, pp. 1-25 (2022).
https://doi.org/10.1007/s11042-022-12500-3
Sawatzki, J., Schlippe, T., Benner-Wickner, M. (2022). Deep Learning Techniques for Automatic Short Answer Grading: Predicting Scores for English and German Answers. In: Artificial Intelligence in Education: Emerging Technologies, Models and Applications. AIET 2021.
https://doi.org/10.1007/978-981-16-7527-0_5
Athamneh, A., Alqudah, A., Aqeil, R., Line Voltage Based Distance Relay Using a Multistage Convolutional Neural Network Classifier, (2021) International Review of Electrical Engineering (IREE), 16 (6), pp. 553-565.
https://doi.org/10.15866/iree.v16i6.20962
Fawa'reh, M., Qasaimeh, M., AbuArja, I., Al-Fayoumi, M., Mitigating Deep learning Attacks Against Text Image CAPTCHA Using Arabic Scheme, (2021) International Journal on Communications Antenna and Propagation (IRECAP), 11 (4), pp. 288-296.
https://doi.org/10.15866/irecap.v11i4.20375
Bal-Ghaoui, M., El Yousfi Alaoui, M., Jilbab, A., Bourouhou, A., Enhanced Ultrasound Breast Cancer Classification Based on Sparse Data and Two Customized Deep Learning Approaches, (2022) International Review on Modelling and Simulations (IREMOS), 15 (3), pp. 146-153.
https://doi.org/10.15866/iremos.v15i3.21504
Ghintab, S., Hassan, M., Localization for Autonomous Vehicles Based on Deep Learning Network, (2023) International Review of Electrical Engineering (IREE), 18 (2), pp. 128-135.
https://doi.org/10.15866/iree.v18i2.22581
Tolebi, G., Dairbekov, N., Kurmankhojayev, D., Link Flow Estimation on an Isolated Intersection Based on Deep Learning Models, (2020) International Review of Automatic Control (IREACO), 13 (1), pp. 19-26.
https://doi.org/10.15866/ireaco.v13i1.18213
Refbacks
- There are currently no refbacks.
Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2024 Praise Worthy Prize
