Packet Loss Concealment Using Deep Neural Networks for CS-CELP-Type Speech Coders in VoIP
DOI:
https://doi.org/10.66950/c6yaqe43Keywords:
Voice Internet Protocol (VoIP), CS-CELP, Coder G.729, Packet Loss Concealment, Deep Neural Network, Packet LossAbstract
Packet loss in Voice over Internet Protocol (VoIP) communications can significantly degrade speech quality, particularly affecting Conjugate-Structure Code-Excited Linear Prediction (CS-CELP) type speech coders like G.729. Traditional Packet Loss Concealment (PLC) methods often struggle with consecutive frame losses. Recent advancements in deep learning have introduced Deep Neural Networks (DNNs) as a promising solution for PLC. This article explores the integration of DNNs into PLC for CS-CELP-type speech coders, focusing on methodologies, experimental setups, results, and future directions.
References
(1) A. Bakri, K. Mahdjane, A. Amrouche, A. Krobba, “Improved G723.1 Codec Speech Quality Under Burst Packet Loss Conditions”, Proc. 5th International Conference On Electrical Engineering and Control Applications (ICEECA), 15–17 November 2022, Khenchela, Algeria, pp 277–287, Part of the book series: Lecture Notes in Electrical Engineering (LNEE) Vol. 1224, 03 september 2024, Springer, Singapore. https://doi.org/10.1007/978-981-97-4776-4_28 DOI: https://doi.org/10.1007/978-981-97-4776-4_28
(2) A. Bakri, A. Amrouche, “Packet loss concealment-based estimation of polynomial interpolation for improving speech quality in VoIP”, International Journal of Intelligent Systems Technologies and Applications”, Vol. 19, N. 5, , 2020, pp. 486-499. DOI: https://doi.org/10.1504/IJISTA.2020.111066
https://doi.org/10.1504/IJISTA.2020.111066 DOI: https://doi.org/10.1504/IJISTA.2020.111066
(3) T. Hori, R. Astudillo, T. Hayashi, Y. Zhang, S. Watanabe and J. Le Roux, "Cycle-consistency Training for End-to-end Speech Recognition," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK, pp. 6271-6275, https://doi.org/10.1109/ICASSP.2019.8683307 DOI: https://doi.org/10.1109/ICASSP.2019.8683307
(4) Z. Zhang, Y. Shen and D. S. Williamson, "Objective Comparison of Speech Enhancement Algorithms with Hearing Loss Simulation," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK, pp. 6845-6849, https://doi.org/10.1109/ICASSP.2019.8683040 DOI: https://doi.org/10.1109/ICASSP.2019.8683040
(5) N. I. Park, J. A. Kang, S. R. Lee, H. K. Kim, "A Packet Loss Concealment Technique Improving Quality of Service for Wideband Speech Coding in Wireless Sensor Networks." International Journal of Distributed Sensor Networks, Vol. 10, Issue 4, 2014, https://doi.org/10.1155/2014/852798 DOI: https://doi.org/10.1155/2014/852798
(6) S. Pascual, A. Bonafonte, and J. Serra, "SEGAN: Speech Enhancement Generative Adversarial Network," in Proc. 18th Annual Conference of the International Speech Communication Association (Interspeech), August 20–24, 2017, Stockholm, Sweden, pp. 3642–3646. https://doi.org/10.21437/Interspeech.2017-1428 DOI: https://doi.org/10.21437/Interspeech.2017-1428
(7) Liu, B., Song, Q., Yang, M., Yuan, W., & Wang, T. (2022). PLCNet: Real-time Packet Loss Concealment with Semi-supervised Generative Adversarial Network. Proc. of Interspeech conference 18-22 September 2022, 575-579. https://doi.org/10.21437/interspeech.2022-10428 DOI: https://doi.org/10.21437/Interspeech.2022-10428
(8) A. Bakri, A. Amrouche, M. Abbas,
L. Bouchakour “Automatic Speech Recognition for VoIP with Packet Loss Concealment”. Procedia Computer Science”. Vol. 128, 2018, p. 72-78. https://doi.org/10.1016/j.procs.2018.03.010 DOI: https://doi.org/10.1016/j.procs.2018.03.010
(9) J.-M. Valin, A. Mustafa, C. Montgomery, T. B. Terriberry, M. Klingbeil, P. Smaragdis, and A. Krishnaswamy, "Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model" Proceedings of Interspeech conference 18-22 September 2022, Incheon, Korea, pp. 570–574. https://doi.org/10.21437/Interspeech.2022-903 DOI: https://doi.org/10.21437/Interspeech.2022-903
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adil BAKRI, Boumediene KHAOUANI , Djamaleddine BERRABAH (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Authors retain copyright and grant the journal right of first publication.
