Speaker Identification Through Natural and Whisper Speech Signal

  • Amrita Singh
  • Amit M. JoshiEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 546)


The paper presents the identification of a speaker with the help of natural and whisper speech signal. The speaker identification through whisper is also useful in cases where the speaker is unable to speak, or speaker wants to hide his/her identity. However, the changes in whispering speech due to the vocal effort have several challenges in maintaining system accuracy. The accuracy of speaker identification is calculated with Mel Frequency Cepstral Coefficient (MFCC) algorithm and Exponential Frequency Cepstral Coefficient (EFCC) algorithm. MFCC and EFCC are considered for feature extraction. All the samples are clustered using K-means algorithm and Gaussian Mixture Model for feature classification. GMM is containing mean, variance, and weight which are modeling parameters. Here Expectation–Maximization algorithm is used for testing the samples and reestimate the parameters. Finally, GMM algorithm recognizes the speaker that exactly matches for a given database. The algorithms are implemented on MATLAB tool, and the results are also verified.


EFCC GMM MFCC Feature extraction K-means 


  1. 1.
    Fan X, Hansen, JHL (2008) Speaker identification for whispered speech based on frequency warping and score competition. In: Ninth annual conference of the international speech communication association, pp 1313–1316Google Scholar
  2. 2.
    Shukla UP., Patel NB, Joshi AM (2013) A survey on recent advances in speech compressive sensing. In: 2013 international multi-conference on automation, computing, communication, control and compressed sensing (iMac4s), pp 276–280. IEEEGoogle Scholar
  3. 3.
    Bahdanau D, Chorowski J, Serdyuk D, Brakel P, Bengio Y (2016) End-to-end attention-based large vocabulary speech recognition. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4945–4949Google Scholar
  4. 4.
    Xiong W, Droppo J, Huang X, Seide F, Seltzer M, Stolcke A, Yu D, Zweig G (2017) The Microsoft 2016 conversational speech recognition system. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5255–5259. IEEEGoogle Scholar
  5. 5.
    Bhadoria BS, Shukla U, Joshi AM (2014) Comparative analysis of basis & measurement matrices for non-speech audio signal using compressive sensing. In: 2014 IEEE international conference on computational intelligence and computing research (ICCIC), pp 1–5. IEEEGoogle Scholar
  6. 6.
    Xiong W, Droppo J, Huang X, Seide F, Seltzer M, Stolcke A, Yu D, Zweig G (2016) Achieving human parity in conversational speech recognition. arXiv preprint arXiv:1610.05256
  7. 7.
    Sak H, Senior A, Rao K, Irsoy O, Graves A, Beaufays F, Schalkwyk J (2015) Learning acoustic frame labeling for speech recognition with recurrent neural networks. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4280–4284. IEEEGoogle Scholar
  8. 8.
    Bimbot F, Bonastre JF, Fredouille C, Gravier G, Magrin Chagnolleau I, Meignier S, Merlin T, Ortega-Garcia J, Petrovska Delacreetaz D, Reynolds DA (2004) A tutorial on text-independent speaker verification. EURASIP J Signal Process 4. Hindawi Publishing Cor-poration, pp 430–451Google Scholar
  9. 9.
    ShuklaUP, Patel NB, Joshi AM (2013) Analysis of music signal compression with compressive sensing. Int J Comput Appl 70(26)Google Scholar
  10. 10.
    Bou-Ghazale SE, Hansen JHL (2000) A comparative study of traditional and newly proposed features for recognition of speech under stress. IEEE Trans Speech Audio Process 8(4):429–442. Prentice Hall, Upper Saddle River, NJ, USAGoogle Scholar
  11. 11.
    Zhou G, Hansen JHL, Kaiser JF (2001) Nonlinear feature based classification of speech under stress. IEEE Trans Speech Audio Process 9(3):201–216CrossRefGoogle Scholar
  12. 12.
    Li X (2004) Reconstruction of speech from Chinese Whispers. PhD, Nanjing University, China; Ito T, Takeda K Itakura F (2005) Analysis and recognition of whispered speech. Speech Commun 45:139–152Google Scholar
  13. 13.
    Jin Q, Jou SCS, Schultz T (2007) Whispering speaker identification. In: 2007 IEEE international conference on multimedia and expo, pp 1027–1030. IEEEGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Malaviya National Institute of Technology JaipurJaipurIndia

Personalised recommendations