Robust noise feature extraction for efficient classification

Rupalee Dwivedi; Utkarsh Singh; Vaibhav Gupta

Rupalee Dwivedi Student, Department of Electronics and communication, JSS Academy, Noida, Uttar Pradesh, India
Utkarsh Singh Student, Department of Electronics, and communication, JSS Academy, Noida, Uttar Pradesh, India
Vaibhav Gupta Student, Department of Electronics, and communication, JSS Academy, Noida, Uttar Pradesh, India

Abstract

In current paper, authors try to investigate regarding robust noise parameter to be used for efficient noise classification in noise parameter analysis which will then be used for intelligent volume control. One hundred and twenty original noises from environment were recorded with the help of a microphone connected to personal computer and stored as a noise samples in the computer’s memory. We have used MATLAB software for the software implementation of noise parameter analysis. Built-in programs have been used for Linear predictive coding (LPC) and Real cepstral parameter (RCEP) whereas user defined program was written for Mel Frequency Cepstral coefficient (MFCC) to get variation in noise parameters which may be further used for analysing the noise samples and classified through any one of the soft computing techniques viz. neural networks, fuzzy logic, genetic algorithms or a combination of these. Forty samples each of three commonly encountered environmental noises (car, market and train) i.e., 120 noises in total have been considered in our study for estimation of three coefficients viz. Mel Frequency Cepstral coefficient, Linear predictive coding and real cepstral parameter. Our experimental results show that Mel Frequency Cepstral Frequencies are robust features for finding out variation in noise parameter estimates.

How to cite this article:
Mishra BP, Dwivedi R, Singh U et al. Robust Noise Feature Extraction for Efficient Classification. J Adv Res Sig Proc Appl 2021; 3(2): 1-5.

References

[1]. Picheny, M.; Nahamoo, D.; Goel, V.; Kingsbury, B.; Ramabhadran, B.; Rennie, S. J.; Saon, G.; , "Trends and advances in speech recognition," IBM Journal of Research and Development , vol.55, no.5, pp.2:1-2:18, Sept.-Oct. 2011
[2]. Mitra, V.; Hosung Nam; Espy-Wilson, C.Y.; Saltzman, E.; Goldstein, L.; , "Articulatory Information for Noise Robust Speech Recognition," Audio, Speech, and Language Processing, IEEETransactions on , vol.19, no.7, pp.1913-1924, Sept. 2011
[3]. Md. Danish Nadeem; Dr. B .P Mishra Variation in Noise Parameter Estimates for Background Noise Classification; ISSN: 2278-0181; Vol. 3 Issue 2, February – 2014
[4] Itakura, F. and Saito, S.Speech information compression based on the maximum likelihood spectrum estimation. Journal of the Acoustical Society of Japan 27 (1971):463-470. [13] F. Beritelli, S. Casale, G. Ruggeri, “New Results in Fuzzy Pattern Classification ofr Background Noise”, Proceedings of ICSP 2000.
[5] W.C. Treurniet and Y. Gong, “Noise independent speech recognition for a variety of noise types”, Proc. IEEE ICASSP 94 Adelaide, pp. 437-440, April 1994.
[6] F. beritelli, S. Casale, “Background Noise Classification in Advanced VBR Speech Coding for Wireless Communications”, Proc. 6th IEEE International Workshop on Intelligent Signal Processing And Comunication systems (ISPACS98), Melbourne, Australia, 4-6 Nov. 1998,pp. 451-455.
[7] Khaled El-Maleh, Ara Samouelian, Peter Kabal, “Frame-Level Noise Classification in Mobile Environments” ICASSP 99, Phoenix, Arizona, May 15-19, 1999. (3)