A Novel Turbo ICI & ICI DSP Cancellation Technique for FBMC-OQAM through a Doubly Selective Channel

  • Hemant Subhash Badodekar VTU Research Scholar
  • Rakesh Subhash Badodekar VTU Research Scholar
  • Dr B.G Nagaraja VTU Research Supervisor
Keywords: Voice Activity Detection (VAD), Wavelet Transform, Signal-to-Noise Ratio (SNR), Noise-robust Speech Processing, Frame Error Rate (FER).

Abstract

Voice Activity Detection (VAD) plays a crucial role in various speech processing appli- cations, such as speech recognition, telecommunication, and speech enhancement. Traditional VAD methods, however, struggle to maintain high accuracy in noisy environments, particularly when the Signalto-Noise Ratio (SNR) is low. This paper explores the use of wavelet transform-based techniques to improve VAD performance in real-world noisy environments. Two wavelet transform-based VAD algorithms, Algorithm-1 and Algorithm2, are introduced and evaluated across four different noise types (airport, babble, restaurant, and station) and at four SNR levels (0 dB, 5 dB, 10 dB, and 15 dB). The performance of the algorithms is measured using two objective metrics: Frame Error Rate (FER) and F1 score. The results show that Algorithm-2 outperforms Algorithm-1 in all tested conditions, offering lower FER and higher F1 scores, demonstrating its robustness in noise-robust VAD. These findings suggest that wavelet transform-based methods provide a promising solution for improving VAD performance, particularly in challenging acoustic environments with varying noise conditions.

References

[1] Wang, Z., & Zhang, Y. (2020). Wavelet-based methods for speech enhancement in noisy environments. Springer.
[2] Cohen, I., & Berdugo, B. (2001). Noise reduction algorithms: A comparison. Signal Pro- cessing, 81(11), 2403-2417.
[3] Kinoshita, S., & Suzuki, T. (2019). A novel wavelet transform-based method for voice activity detection in noisy speech signals. IEEE Transactions on Audio, Speech, and Lan- guage Processing, 27(4), 680-692.
[4] Mahajan, A., & Raghav, P. (2022). Advances in Voice Activity Detection for Speech Pro- cessing. Wiley.
[5] Nayak, A., & Das, A. (2018). A comparative analysis of VAD algorithms in real-time speech processing. Journal of Signal Processing Systems, 90(3), 511-522.
[6] Gupta, R., & Sharma, P. (2021). A deep learning approach for noiserobust voice activity detection. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1-5.
[7] Yang, H., & Wang, D. (2017). A comprehensive review of noise robust voice activity detection methods. Journal of Acoustic Society of America, 141(2), 732-746.
[8] Zhang, L., & Yang, S. (2020). Wavelet-based features for VAD in speech recognition sys- tems. International Journal of Speech Technology, 23(1), 1-10.
[9] Zhang, X., & Wu, Z. (2019). Voice activity detection using wavelet transform and support vector machine. Signal Processing Letters, 26(4), 700-704.
[10] Saito, S., & Inoue, K. (2018). Comparative analysis of frame-based VAD techniques in noisy environments. IEEE Transactions on Signal Processing, 66(7), 1878-1892.
[11] Boulianne, L., & Gagnon, L. (2015). Performance evaluation of speech enhancement and VAD techniques for robust speech recognition in noisy environments. IEEE Transactions on Audio, Speech, and Language Processing, 23(8), 1479-1491.
[12] Xie, L., & Zhang, X. (2020). Deep learning-based voice activity detection in noisy environments. IEEE Access, 8, 45599-45608.
[13] Raj, B., & Pellom, B. (2001). A comparison of speech activity detection algorithms for telephone applications. IEEE Transactions on Speech and Audio Processing, 9(1), 39-48.
[14] Xu, D., & Liu, M. (2021). Robust voice activity detection in challenging acoustic environments using wavelet transforms. Journal of Acoustic Society of America, 149(5), 2907-2917.
[15] Zeng, Y., & Li, X. (2022). Speech activity detection in the presence of noise using the wavelet transform. IEEE Transactions on Circuits and Systems for Video Technology, 32(6), 3372-3383.
[16] Ozdogan, M., & Selen, Y. (2020). Performance analysis of voice activity detection algorithms based on wavelet transforms. International Journal of Speech and Language Pro- cessing, 7(3), 105116.
[17] Yegnanarayana, B., & Rao, M. (2019). Fundamentals of Speech Recognition. Prentice-Hall.
Published
2025-12-10
How to Cite
Badodekar, H., Badodekar, R., & Nagaraja, D. B. (2025). A Novel Turbo ICI & ICI DSP Cancellation Technique for FBMC-OQAM through a Doubly Selective Channel. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 11(1), 119-122. Retrieved from http://asianssr.org/index.php/ajct/article/view/1474

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.