Noise Reduction using Modified Central Frequency BWT and RLS filter

Authors

  • Shraddha C. Vidyavardhaka College of Engineering, Mysuru, affiliated to Visvesvaraya Technological University, Belagavi, INDIA
  • Chayadevi M. L. B.N.M. Institute of Technology, Bangalore, affiliated to Visvesvaraya Technological University, Belagavi, INDIA
  • M. A. Anusuya JSS Science and Technology University, Mysuru, INDIA
  • Vani H. Y. JSS Science and Technology University, Mysuru, INDIA

Keywords:

Empirical Mode Decomposition, Lease Mean Square, Modified Central Frequency Bionic Wavelet Transform, Noise Reduction, Normalized Least Mean Square, Recursive Least Square

Abstract

Speech signals are majorly mixed with different types of noises namely background noise, environmental noise, white noise, colored noise and so on. To have an efficient speech recognition system, it is necessary to have noisy speech signals preprocessed to reduce their noise levels. Very few works are addressed to handle pink and babble noises. Hence, we were motivated to design and apply hybrid algorithms to handle these types of noises. A new hybrid Modified Central Frequency Bionic Wavelet transform using Recursive Adaptive Filter is proposed as a novel method to increase the signal strength. This method is evaluated using MSE, SNR and PSNR parameters. Among these SNR and PSNR metrics has been observed to yield better results for pink and babble noises.

Downloads

Download data is not yet available.

References

Kapoor Janak, Mishra G. R., Pathak Ajita & Rai, Manish. Analysis of BSC and AWGN Channel Distortion Effect on Sound Signal in Active Noise Cancellation Application, Engineering Letters, 29(2021), 926-930.

Suryawanshi I P & Manjare C A. Speech signal analysis and enhancement based on HNM synthesis. In Int conf comput commu and autom (Pune, India) 12-13 August 2016, Doi: 10.1109/ICCUBEA.2016.7860100.

Shraddha. C, Chayadevi. M L and M. A. Anusuya. Noise Cancellation and Noise Reduction Techniques: A Review. In IEEE International Conference on Advances in Information Technology, Chikmagalur, India. pp. 159-166, 2019, Doi: 10.1109/ICAIT47043.2019.8987262.

Y. Kopsinis and S. McLaughlin. Development of EMD-Based Denoising Methods Inspired by Wavelet Thresholding. In IEEE Transactions on Signal Processing, vol. 57, pp. 1351-1362, 2009, Doi: 10.1109/TSP.2009.2013885.

H. Touati and K. Khaldi. Speech Denoising by Adaptive Filter LMS in the EMD Framework. International Multi-Conference on Systems, Signals & Devices (SSD), Yasmine Hammamet, Tunisia, pp. 1-4, 2018, Doi: 10.1109/SSD.2018.8570709.

Wahbi Nabi, Mohamed Ben Nasr, Noureddine Aloui, Adnane Cherif. A dual-channel noise reduction algorithm based on the coherence function and the bionic wavelet. Journal of Applied Aoustics, pp. 186-191, 2018, Doi: 10.1016/j.apacoust.2017.11.003.

Norezmi Jamal, N. Fuad and MNAH. Shaabani. A Hybrid Approach for Single Channel Speech Enhancement using Deep Neural Network and Harmonic Regeneration Noise Reduction. International Journal of Advanced Computer Science and Applications (IJACSA), vol. 11, 2020, Doi: 10.14569/IJACSA.2020.0111033.

H Y Vani, M A Anusuya and M L Chayadevi. Morlet-Kernel Principal Component Analysis Features for Speech Recognition. Journal of Computational and Theoretical Nanoscience, vol.17, pp.4482-4486,2020, Doi: 10.1166/jctn.2020.9102.

Anil Garg & O. P. Sahu. A hybrid approach for speech enhancement using Bionic wavelet transform and Butterworth filter. International Journal of Computers and Applications, pp. 1-10, 2019, doi: 10.1080/1206212X.2019.1614293.

Mbachu C. B, Akaneme S.A. Noise Reduction in Speech Signals Using Recursive Least Square Adaptive Algorithm. International Journal of Engineering and Advanced Technology Studies, vol. 8, pp.1-7, 2020.

Mowlaee P, Stahl J, Kulmer J. Iterative joint MAP single-channel speech enhancement given non-uniform phase prior. Speech Communication, pp. 85–96, 2017, Doi: 10.1016/j.specom.2016.11.008.

Swathi Kotte. Performance Analysis of Adaptive Algorithms based on different parameters Implemented for Acoustic Echo Cancellation in Speech Signals. Ph D Thesis, Blekinge Institute of Technology, Sweden, 2011.

Sagar Reddy Vumanthala, Bikshalu Kalagadda. Real-time speech enhancement using optimised empirical mode decomposition and non-local means estimation. Journal of Institute of Engineering Technology Computers & Digital Techniques,vol. 14, 290-298, 2020, Doi: 10.1049/iet-cdt.2020.0034.

R. Gary Leonard, and George Doddington. TIDIGITS LDC93S10. Web Download. Philadelphia: Linguistic Data Consortium, 1993, doi.org/10.35111/72xz-6x59.

Varga, A, Steeneken, H. Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Journal of Speech Communication, vol. 12, pp. 247–251, 1993. Doi: 10.1016/0167-6393(93)90095-3.

R. Martinek, R. Jaros, J. Baros, L. Danys, A. Kawala-Sterniuk. Noise reduction in industry based on virtual instrumentation. Computers, Materials & Continua, vol. 69, pp. 1073–1096, 2021, Doi: 10.32604/cmc.2021.017568.

Downloads

Published

11.01.2024

How to Cite

C. , S. ., M. L., C. ., Anusuya, M. A. ., & H. Y., V. . (2024). Noise Reduction using Modified Central Frequency BWT and RLS filter. International Journal of Intelligent Systems and Applications in Engineering, 12(11s), 512–521. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4471

Issue

Vol. 12 No. 11s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.