Novel Turbo Cancellation ISI/ICI DSP Concepts for FBMC-OQAM Based MIMO 5G Digital Communication Multi-Carrier Systems

  • Hemant Subhash Badodekar
  • Rakesh Subhash Badodekar
  • Dr B.G Nagaraja
Keywords: VAD; ZCR; CNN; Metrics; Databases

Abstract

This article provides an all-encompassing survey on voice activity detection (VAD) a critical component crucial to speech processing systems responsible for detecting speech presence within an audio signal. The presented survey covers fundamental aspects related to VAD including its importance, applications, and inherent challenges faced during implementation. Our exploration initiates with establishing a solid foundation concerning the basics of VAD encompassing features and techniques in detail. Additionally key issues encountered along with challenges faced when implementing this technology efficiently is addressed. Fur- thermoses, it also delves into evaluation metrics commonly utilized for assessing overall performance whilst providing a comprehensive overview of readily accessible VAD databases. Overall, this survey predominantly presents a clear comprehend- Sion of VAD, the encountered challenges and the utilized techniques designed to overcome them ultimately serving as an esteemed resource for both researchers and professionals functioning within the speech processing field.

References

[1] Makhlouf, A., Lazli, L. and Bensaker, B., 2016. Evolutionary structure of hidden Markov models for audio-visual Arabic speech recognition. International Journal of Signal and Imaging Systems Engineering, 9(1), pp.55-66.
[2] Nagaraja, B.G. and Jayanna, H.S., 2016. Feature extraction and modelling tech- niques for multilingual speaker recognition: a review. International Journal of Signal and Imaging Systems Engineering, 9(2), pp.67-78.
[3] Ramirez, J., G´orriz, J.M. and Segura, J.C., 2007. Voice activity detection. funda- mentals and speech recognition system robustness. Robust speech recognition and understanding, 6(9), pp.1-22.
[4] Jainar, S.J., Sale, P.L. and Nagaraja, B.G., 2020. VAD, feature extraction and mod- elling techniques for speaker recognition: a review. International Journal of Signal and Imaging Systems Engineering, 12(1-2), pp.1-18.
[5] Heo, Y. and Lee, S., 2023. Supervised Contrastive Learning for Voice Activity De- tection. Electronics, 12(3), p.705.
[6] Graf, S., Herbig, T. and Buck, M., 2023. 13 Voice Activity Detection for In-Car Communication Systems. Towards Human-Vehicle Harmonization, 3, p.163.
[7] Zhu, Z. and Pei, K., A Robust Soft Voice Activity Detection Algorism Based on Multi-Feature Fusion Cosine Similarity at Low Signal-toNoise Ratio. Available at SSRN 4345665.
[8] Bendoumia, R., Hassani, I. and Guessoum, A., 2023. Recursive adaptive filtering algorithms for sparse channel identification and acoustic noise reduction. Analog Integrated Circuits and Signal Processing, 114(1), pp.51-73.
[9] Chien, Y.R., Zhou, M., Peng, A., Zhu, N. and Torres-Sospedra, J., 2023. Signal Processing and Machine Learning for Smart Sensing Applications. Sensors, 23(3), p.1445.
[10] Pang, J., 2017, January. Spectrum energy-based voice activity detection. In 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 1-5). IEEE.
[11] Tan, Y.W., Liu, W.J., Jiang, W. and Zheng, H., 2014, July. Hybrid svm/hmm architectures for statistical model-based voice activity detection. In 2014 International Joint Conference on Neural Networks (IJCNN) (pp. 2875-2878). IEEE.
[12] Ouahabi, S.E., Atounti, M. and Bellouki, M., 2020. HMM-GMM based Amazigh speech recognition system. International Journal of Signal and Imaging Systems Engineering, 12(1-2), pp.47-53.
[13] Sholokhov, A., Sahidullah, M. and Kinnunen, T., 2018. Semisupervised speech ac- tivity detection with an application to automatic speaker verification. Computer Speech & Language, 47, pp.132-156.
[14] Ouahabi, S.E., Atounti, M. and Bellouki, M., 2020. HMM-GMM based Amazigh speech recognition system. International Journal of Signal and Imaging Systems Engineering, 12(1-2), pp.47-53.
[15] Sandabad, S., Benba, A., Tahri, Y.S. and Hammouch, A., 2016. Novel extraction and tumour detection method using histogram study and SVM classification. Inter- national Journal of Signal and Imaging Systems Engineering, 9(4-5), pp.202-208.
[16] Fredj, I.B., Zouhir, Y. and Ouni, K., 2018. Fusion features for robust speaker identification. International Journal of Signal and Imaging Systems Engineering, 11(2), pp.65-72.
[17] Tan, Z.H. and Dehak, N., 2020. rVAD: An unsupervised segmentbased robust voice activity detection method. Computer speech & language, 59, pp.1-21.
[18] Ashwini, B. and Yuvaraju, B.N., 2017. Application of machine learning approach in detection and classification of cars of an image. International Journal of Signal and Imaging Systems Engineering, 10(1-2), pp.8-13.
[19] Graf, S., Herbig, T., Buck, M. and Schmidt, G., 2015. Features for voice activity detection: a comparative analysis. EURASIP Journal on Advances in Signal Pro- cessing, 2015, pp.1-15.
[20] Drugman, T., Stylianou, Y., Kida, Y. and Akamine, M., 2015. Voice activity detection: Merging source and filter-based information. IEEE Signal Processing Letters, 23(2), pp.252-256.
[21] Sehgal, A. and Kehtarnavaz, N., 2018. A convolutional neural network smartphone app for real-time voice activity detection. IEEE Access, 6, pp.9017-9026.
[22] Bai, Y., Yi, J., Tao, J., Wen, Z. and Liu, B., 2019, November. Voice activity detection based on time-delay neural networks. In 2019 AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 1173- 1178). IEEE.
[23] Zhang, X.L. and Xu, M., 2022. AUC optimization for deep learningbased voice activity detection. EURASIP Journal on Audio, Speech, and Music Processing, 2022(1), pp.1-12.
[24] Lee, J., Jung, Y. and Kim, H., 2020. Dual attention in time and frequency domain for voice activity detection. arXiv preprint arXiv:2003.12266.
[25] Martinelli, F., Dellaferrera, G., Mainar, P. and Cernak, M., 2020, May. Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 8544-8548). IEEE.
[26] Neo, V.W., Weiss, S., McKnight, S.W., Hogg, A.O. and Naylor, P.A., 2022, September. Polynomial eigenvalue decomposition-based target speaker voice activity detection in the presence of competing talkers. In 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) (pp. 1-5). IEEE.
[27] Rho, D., Park, J. and Ko, J.H., 2022. Nas-vad: Neural architecture search for voice activity detection. arXiv preprint arXiv:2201.09032.
[28] Tong, S., Gu, H. and Yu, K., 2016, March. A comparative study of robustness of deep learning approaches for VAD. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5695-5699). IEEE.
[29] Nautsch, A., Bamberger, R. and Busch, C., 2016, September. Decision robustness of voice activity segmentation in unconstrained mobile speaker recognition environments. In 2016 International Conference of the Biometrics Special Interest Group (BIOSIG) (pp. 1-7). IEEE.
[30] Jayaprakash H., and Nagaraja B. G., 2020, A comparison of features for voice activity detection - a review and some experimental results, Vidyabharati International Interdisciplinary Research Journal, 9(2) (pp. 91-94)
[31] Zue, V., Seneff, S. and Glass, J., 1990. Speech database development at MIT: TIMIT and beyond. Speech communication, 9(4), pp.351356.
[32] Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F. and Matassoni, M., 2013, December. The second ‘CHiME’ speech separation and recognition challenge: An overview of challenge systems and outcomes. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (pp. 162-167). IEEE.
[33] Nagrani, A., Chung, J.S. and Zisserman, A., 2017. VoxCeleb: a largescale speaker identification dataset. arXiv preprint arXiv:1706.08612.
[34] Snyder, D., Chen, G. and Povey, D., 2015. Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484.
[35] Thiemann, J., Ito, N. and Vincent, E., 2013, June. The diverse environments multi- channel acoustic noise database (demand): A database of multichannel environmental noise recordings. In Proceedings of Meetings on Acoustics ICA2013 (Vol. 19, No. 1, p. 035081). Acoustical Society of America.
[36] Panayotov, V., Chen, G., Povey, D. and Khudanpur, S., 2015, April. Librispeech: an as corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5206-5210). IEEE.
[37] Ardila, R., Branson, M., Davis, K., Henretty, M., Kohler, M., Meyer, J., Morais, R., Saunders, L., Tyers, F.M. and Weber, G., 2019. Common voice: A massively- multilingual speech corpus. arXiv preprint arXiv:1912.06670.
[38] Hu, Y. and Loizou, P.C., 2007. Evaluation of objective quality measures for speech enhancement. IEEE Transactions on audio, speech, and language processing, 16(1), pp.229-238.
[39] Ma, J., Hu, Y. and Loizou, P.C., 2009. Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. The Journal of the Acoustical Society of America, 125(5), pp.3387-3405.
[40] A.A. Zamyatnin, A.S. Borchikov, M.G. Vladimirov, O.L. Voronina, The EROP- Moscow oligopeptide database, Nucleic acids research,
34 (suppl 1) D261-D266 (2006)
Published
2025-12-10
How to Cite
Badodekar, H., Badodekar, R., & Nagaraja, D. B. (2025). Novel Turbo Cancellation ISI/ICI DSP Concepts for FBMC-OQAM Based MIMO 5G Digital Communication Multi-Carrier Systems. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 11(1), 109-118. Retrieved from http://asianssr.org/index.php/ajct/article/view/1471

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.