A Novel Isolated Speech Recognition Method Based on Neural Network

  • Guojiang Fu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 220)


The Radial Basis Function Neural Network architecture has been shown to be suitable for the recognition of isolated words. Recognition of words is carried out in speaker-dependent mode. In this mode the tested data presented to the network are the same as the trained data. The 16 Linear Predictive Cepstral Coefficients with 16 parameters from each frame improves a good feature extraction method for the spoken words, since the first 16 in the cepstrum represent most of the formant information. It is found that the performance of radial basis function neural network (RBF) classifier is superior to MLP classifier. It is found that speaker 6 average performances is the best performance in training MLP classifier and speaker 2 average performances is the best performance in training RBF classifier. It is found that average speaker 4 performances is the best performance in testing MLP classifier and speaker 1 average performance is the best performance in testing RBF classifier.


Neural network Speech recognition Multilayer perception 


  1. 1.
    Benyettou A (1995) Acoustic phonetic recognition in the arabex system. Int Work Shop Robot Hum Commun ATIP95 44:34–45Google Scholar
  2. 2.
    Al-Alaoui MA, Mouci R, Mansour MM, Ferzli R (2002) A cloning approach to classifier training. IEEE Trans Syst Man Cybern Part A Syst Hum 32(6):746–752Google Scholar
  3. 3.
    Picton P (2000) Neural networks, vol 35. Palgrave, NY, pp 145–157Google Scholar
  4. 4.
    Tan Lee, Ching PC, Chan LW (1998) Isolated word recognition using modular recurrent neural networks. Pattern Recogn 31(6):751–760CrossRefGoogle Scholar
  5. 5.
    Gurney K (1997) An introduction to neural networks, UCL Press, University of Sheffield, SheffieldGoogle Scholar
  6. 6.
    Berthold MR (1994) A time delay radial basis function for phoneme recognition. In: Proceedings of international conference on neural network, vol 33. Orlando, USA, pp 102–109Google Scholar
  7. 7.
    Rabiner L, Juang B–H (1993) Fundamentals of speech recognition, vol 213. PTR Prentice Hall, San Francisco, pp 378–385Google Scholar
  8. 8.
    Kandil N, Sood VK, Khorasani K, Patel RV (1992) Fault identification in an AC–DC transmission system using neural networks. IEEE Trans Power Syst 7(2):812–819CrossRefGoogle Scholar
  9. 9.
    Morgan D, Scolfield C (1991) Neural networks and speech processing, vol 9. Kluwer Academic Publishers, Berlin, pp 46–53Google Scholar
  10. 10.
    Park DC (1991) M A El-Sharakawi and Ri Marks II electric load forecasting using artificial neural networks. IEEE Trans Power Syst 6(2):442–449CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.Information and Control Engineering Institute, Shenyang Jianzhu UniversityShenyangChina

Personalised recommendations