In this paper, reconstruction of speech signal is performed using a novel technique Empirical Mode Decomposition (EMD). EMD is mainly applicable for non-linear and non –stationary signals and therefore applicable for speech which is non linear and non-stationary. EMD is applied for finding the glottal source signal of speech which provide us the source information and then vocal tract filter is found out and original speech is reconstructed. Speech samples are collected from different Assamese dialect and the experimental result derived establishes the effectiveness of the proposed method

Speech, Empirical Mode Decomposition (EMD), Intrinsic Mode Function (IMF), Fourier Transform (FT)

[1] A. Bouzid, N. Ellouze, “ EMD Vocal Tract Frequency Analysis of Speech Signal”, 4th International Conference Sciences of Electronic, Technologies of Information and Telecommunications , PP TUNISIA
[2] S. S. Sheth ,“Extraction of Pitch from Speech Signals using Hilbert Huang Transform”.
[3] B. M. Battista, C. Knapp, T. McGee, and V. Goebel, Application of the empirical mode decomposition and Hilbert-Huang transform to seismic reflection data, Geophysics , vol72, PP 29-37, 2007.
[4] T. Hasan and Md. K. Hasan, “Suppression of Residual Noise From Speech Signals Using Empirical Mode Decomposition", IEEE Signal Processing Letters, vol 16, no. 1, Jan 2009.
[5] G. Schlotthauer, M. E. Torres and H. L. Rufiner, “A New Algorithm For Instantaneous F0 Speech Extraction Based On Ensemble Empirical Mode Decomposition”, 17th European Signal Processing Conference (EUSIPCO 2009), 2009.
[6] P. Heydarian and J. D. Reis , “Extraction Of Long-Term Structures In Musical Signals Using The Empirical Mode Decomposition", Proc. of the 8th Int. Conference on Digital Audio Effects (DAFX-05), Madrid, Spain, 2005.
[7] G. Schlotthauer, M. E. Torres and H. L. Rufiner, “Voice Fundamental Frequency Extraction Algorithm Based on Ensemble Empirical Mode Decomposition and Entropies”, Proc. of the World Congress on Medical Physics and Biomedical Engineering, Germany,2009
[8] J. W. Huang and B. Milkereit, “Empirical Mode Decomposition Based Instantaneous Spectral Analysis and its Applications to Heterogeneous Petrophysical Model Construction’’, joint convention of CSPG, CSEG and CWLS, 2009.
[9] G. Rilling , P. Flandrin ,P. Goncalves, “Empirical Mode Decomposition as a Filter Bank”, IEEE Signal Processing Letters, vol. 11, Issue 2, pp- 112 - 114, 2004.
[10] O. Douglas: “Speech communication Human and Machine", IEEE Press, 2nd Ed., , 2000
[11] L. R. Rabiner and and B. H. Juang: “Fundamentals of Speech Recognition", Prentice-Hall, 1993.
[12] N. Goswami, M. Sarma, K.K.Sarma, "Reconstruction of Speech Signal using Empirical Mode Decomposition Based Glottal Source Extraction", In Proceedings of 1st IEEE International Conference on Emerging Trends and Application in Computer Science, pp 27-32, Shillong, India, 2013.
[13] N. Goswami, M. Sarma and K.K.Sarma, "Empirical Mode Decomposition Based Reconstruction of Speech Signal in Noisy Environment", IEEE International Conference on Signal Processing and Integrated Network, Noida, India, 2014.
[14] N. Goswami, M. Sarma and K.K.Sarma,"Effective Speech Signal Reconstruction Technique using Empirical Mode Decomposition Under Various Conditions", Recent Trends in Intelligent and Emerging system Design, Springer, 2015.