Word recognition from speech signal using linear predictive coding and spectrum analysis

  • Authors

    • Mandeep Singh Thapar Institute of Engg. & Tech., PATIALA
    • Gurpreet Singh Thapar Institute of Engg. & Tech., PATIALA
    2018-07-16
    https://doi.org/10.14419/ijet.v7i3.13285
  • Speech Signal Processing, Isolated Word Recognition, Spectrum Analysis, Criminals.
  • This paper presents a technique for isolated word recognition from speech signal using Spectrum Analysis and Linear Predictive Coding (LPC). In the present study, only those words have been analyzed which are commonly used during a telephonic conversations by criminals. Since each word is characterized by unique frequency spectrum signature, thus, spectrum analysis of a speech signal has been done using certain statistical parameters. These parameters help in recognizing a particular word from a speech signal, as there is a unique value of a feature for each word, which helps in distinguishing one word from the other. Second method used is based on LPC coefficients. Analysis of features extracted using LPC coefficients help in identification of a specific word from the input speech signal. Finally, a combination of best features from these two methods has been used and a hybrid technique is proposed. An accuracy of 94% has been achieved for sample size of 400 speech words.

     

     

  • References

    1. [1] D. Miller, “Revealed: Hundreds of words to avoid using online if you don't want the government spying on youâ€, The Daily Mail UK, 26 May 2012.

      [2] J. Leonardo, P. Aguilar, D. Báez-López, Luis Guerrero-Ojeda and J. Rodríguez, “A Voice Recognition System for Speech Impaired Peopleâ€, 14th International Conference on Electronics, Communications and Computers (CONIELECOMP) 2004.

      [3] A. Kumar Paul, D. Das, Md. M. Kamal, “Bangla Speech Recognition System using LPC and ANNâ€, 2009 Seventh International Conference on Advances in Pattern Recognition , 2009.

      [4] A. Nica, A. Caruntu, G. Toderean, O. Buza, “Analysis and Synthesis of Vowels Using Matlabâ€, IEEE, 2006.https://doi.org/10.1109/AQTR.2006.254662.

      [5] D.Ning “Developing an Isolated Word Recognition System in MATLABâ€. Matlab Digest, 2010.

      [6] T. Murakami and Y. Ishida, “Fundamental frequency estimation of speech signals using MUSIC Algorithmâ€, Conference on Acoust. Sci. & Tech., 2001.

      [7] K. Daqrouq, W.A. Sawalmeh, “Speaker Identification Wavelet Transform Based Methodâ€, fifth International Multi-Conference on Systems, Signals and Devices 2008.

      [8] Z. Weng, L. Li, D. Guo, “Speaker Recognition Using Weighted Dynamic MFCC Based on GMMâ€, ASID International Conference, 2010.https://doi.org/10.1109/ICASID.2010.5551341.

      [9] H. Heidari and S. Gobee, "Isolated Word Command Recognition for Robot Navigation", International Symposium on Robotics and Intelligent Sensors 2012.

      [10] E. Chandra, C. Sunitha, “A review on Speech and Speaker Authentication System using Voice Signal feature selection and extractionâ€, IEEE International Advance Computing Conference, 2009.

      [11] R. Fisher, Mclachlan, “The Use of Multiple Measurements in Taxonomic Problemsâ€, 1976.

      [12] M. Singh, S. Singh and S. Gupta, “An information fusion based method for liver classification using texture analysis of ultrasound imagesâ€, Information Fusion, Vol.19, pp 91-96, 2014.https://doi.org/10.1016/j.inffus.2013.05.007.

  • Downloads

  • How to Cite

    Singh, M., & Singh, G. (2018). Word recognition from speech signal using linear predictive coding and spectrum analysis. International Journal of Engineering & Technology, 7(3), 1531-1534. https://doi.org/10.14419/ijet.v7i3.13285