A Hybrid Approach to Gender Classification using Speech Signal
DOI:
https://doi.org//10.32628/IJSRSET196110Keywords:
Wavelet, Neural Networks, Stationary Wavelet Transform, Sampling, Power Spectral Density and Gender Classification.Abstract
Speech forms a significant means of communication and the variation in pitch of a speech signal of a gender is commonly used to classify gender as male or female. In this study, we propose a system for gender classification from speech by combining hybrid model of 1-D Stationary Wavelet Transform (SWT) and artificial neural network. Features such as power spectral density, frequency, and amplitude of human voice samples were used to classify the gender. We use Daubechies wavelet transform at different levels for decomposition and reconstruction of the signal. The reconstructed signal is fed to artificial neural network using feed forward network for classification of gender. This study uses 400 voice samples of both the genders from Michigan University database which has been sampled at 16000 Hz. The experimental results show that the proposed method has more than 94% classification efficiency for both training and testing datasets.
References
- Rajasekaran S. and Vijaylakshmi G. A.(2003). "Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis and Applications", PHI.
- Sivanandam S. N. and Deepa S. N(2011). "Principles of Soft Computing", 2nd Edition, Wiley.
- Crowley, P.(2007). "A Guide to Wavelets for Economists. Journal of Economic Surveys", 21 (2), pp. 207–267.
- Kaijian H., LeanY., Kin K.L.(2012). "Crude oil price analysis and forecasting using wavelet decomposed ensemble model", Journal of Energy and Exergy Modelling of Advance Energy Systems, 46(1), pp.564–574.
- Chang S. G., Yu B., Vetterli M. (2000). "Adaptive wavelet thresholding for image denoising and compression", IEEE Trans. Image Processing, 9(9), pp. 1532-1546.
- Brassarote G.O.N., Souza E.M., Monico J.F.G. (2018). "Non-decimated Wavelet Transform for a Shift-invariant Analysis", Trends in Applied and Computational Mathematics,19(1), pp. 93-110.
- Wani M. I, Farooqi B, Wani N, Mehraj (2018). "Speech Based Gender Classification", Emerging Trends and Innovations in Electronics and Communication Engineering - ETIECE-2017, 5(1), e-ISSN: 2348-4470 .
- Ali M. S, Islamand M. S, Hossain M. A. (2012). "Gender Recognition System Using Speech Signal", International Journal of Computer Science, Engineering and Information Technology, IJCSEIT, 2(1),ISSN: 2231-0711, pp. 118-120.
- Harb H, Chen L.(2003)."Gender Identification Using A General Audio Classifier", Dept. Mathématiques Informatique, Ecole Centrale de Lyon, France.
- Martin A. F, Przybocki M. A.(2001). "Speaker recognition in a multi-speaker environment", 7th European Conference on Speech Communication and Technology, (Eurospeech 2001), Denmark, pp. 787–90.
- Khan A, Kumar V, Kumar S.(2017), "Speech Based Gender Identification Using Fuzzy Logic" International Journal of Innovative Research in Science, Engineering and Technology 6(7), ISSN(Online): 2319-8753, pp. 14344-51.
- Khanum S, Sora M.(2015). "Speech based Gender Identification using Feed Forward Neural Networks", National Conference on Recent Trends in Information Technology, International Journal of Computer Applications , pp 5-8.
- Meena K, Subramaniam K, and Gomathy M.(2013). "Gender Classification in Speech Recognition using Fuzzy Logic and Neural Network", The International Arab Journal of Information Technology, 10( 5), pp. 477-485.
- Prabha M, Viveka P, Sreeja G. B.(2016). "Advanced Gender Recognition System Using Speech Signal", IJCSET , 6(4),pp. 118-120.
- Kaur D.(2014). "Machine Learning Based Gender Recognition and Emotion Detection", International Journal of Engineering Sciences & Emerging Technologies, IJESET, 7(2), ISSN:22316604,pp.646-651.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRSET
This work is licensed under a Creative Commons Attribution 4.0 International License.