ОВОЗ СИГНАЛЛАРИДА ШОВҚИННИ КАМАЙТИРИШ УСУЛЛАРИНИ ТАҲЛИЛ ҚИЛИШ ВА ТАҚҚОСЛАШ
Keywords:
audio signal, noise reduction, Wiener filter, STFT, spectral subtractionAbstract
This paper analyzes noise reduction methods in audio signals and compares their effectiveness. The main focus is on spectral subtraction, Wiener filtering, and spectral masking based on the Short-Time Fourier Transform (STFT). The results show that different methods demonstrate varying performance under different noise conditions, while STFT-based approaches provide higher speech intelligibility.
Downloads
References
1. Özkurt, C.Investigation of the Effectiveness of Audio Processing and Filtering Strategies in Noisy Environments on Speech Recognition Performance. // Osmaniye Korkut Ata University Journal of Science and Technology, 2025, Vol. 8, No. 1, pp. 222–247.
2. Nasir, R. J., Abdulmohsin, H. A.A Hybrid Method for Speech Noise Reduction Using Log-MMSE. // Iraqi Journal of Science, 2025, Vol. 66, No. 2, pp. 860–875.
3. Sainburg, T., Zorea, A.Domain General Noise Reduction for Time Series Signals with Noisereduce. // Scientific Reports, 2025, Vol. 15, Article No. 30905.
4. Yang, X., Huang, G., Jin, J., Chen, J., Benesty, J. Design and Optimization of Superdirective Beamforming and Post-Filtering for Speech Enhancement. // IEEE Conference/Journal (аниқ манбага қараб тўлдирилади), 2023.
5. Kharkov, A., Oliinyk, V., Lukin, V. V., & Krivenko, S. S. (2020). Blind estimation of noise variance for 1D signal denoising. Telecommunications and Radio Engineering, 79(7), 567–581.
6. BRYSIN PETRO. National Aerospace University – KhAI https://orcid.org/0000-0003-2598-3907
7. Wei-Chen Lin . DOI.International Journal of Research in Circuits, Devices and Systems 2026; 7(1) 28-32: https://www.doi.org/10.22271/27084531.2026.
8. Seetharaman P. torch-stft. GitHub. 2022. https://github.com/pseeth/torch-stft
9. Shahamiri SR. Speech vision: An end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2021 29, 852-861;
10. R. a. D. R. Jaiswal, "Implicit wiener filtering for speech enhancement in non-stationary noise," in 2021 11th International Conference on Information Science and Technology (ICIST), Chengdu, China, May. 2021: IEEE, pp. 39-47, DOI: 10.1109/ICIST52614.2021.9440639.
11. H. A. Abdulmohsin, B. Al-Khateeb, S. S. Hasan, and R. Dwivedi, "Automatic illness prediction system through speech," Computers and Electrical Engineering, vol. 102, p. 108224, July. 2022, DOI: https://doi.org/10.1016/j.compeleceng.2022.108224
12. Vellinga, W. Xeno-canto - soundscapes from around the worldhttps://doi.org/10.15468/9u3zaq, (2024). Occurrence dataset accessed via GBIF.org on 2024-10-17.
