A Comparative Study of Isolated Word Recognizer Using SVM and WaveNet

  • John Sahaya Rani Alex
  • Arka Das
  • Suhit Atul Kodgule
  • Nithya Venkatesan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)

Abstract

In this paper, speaker-independent isolated word recognition system is proposed using the Mel-Frequency Cepstral Coefficients feature extraction method to create the feature vector. Support vector machine, sigmoid neural net, and the novel wavelet neural network are used as classifiers and the results are compared in terms of the maximum accuracy obtained and the number of iterations taken to achieve this. The effect of stretch factor on the accuracy of classification for WaveNets is shown in the results. The number of features is also varied using dimension reduction technique and its effect on the accuracies is studied. The data is prepared using feature scaling and dimensionality reduction before training SVM and NN classifiers.

Keywords

Isolated word recogniser Mel-frequency cepstral coefficients Support vector machine Artificial neural network WaveNet 

References

  1. 1.
    Besbes S, Lachiri Z (2016) Multi-class SVM for stressed speech recognition. In: 2016 2nd international conference on advanced technologies for signal and image processing (ATSIP), 21–23 March 2016.  https://doi.org/10.1109/atsip.2016.7523188
  2. 2.
    Padrell-Sendra J, Martín-Iglesias D, Díaz-de-María F (2006) Support vector machines for continuous speech recognition. In: 2006 14th European on signal processing conference, 4–8 Sept 2006Google Scholar
  3. 3.
    Gurban M, Thiran J-P (2005) Audio-visual speech recognition with a hybrid SVM-HMM system. In: 2005 13th European on signal processing conference, 4–8 Sept 2005Google Scholar
  4. 4.
    Riis SK (1998) Hidden neural networks: application to speech recognition. In: Proceedings of the 1998 IEEE international conference on acoustics, speech and signal processing, 1998, 15–15 May 1998.  https://doi.org/10.1109/icassp.1998.675465
  5. 5.
    Barua P, Ahmad K, Khan AAS, Sanaullah M (2014) Neural network based recognition of speech using MFCC features. In: 2014 international conference on informatics, electronics & vision (ICIEV), 23–24 May 2014.  https://doi.org/10.1109/iciev.2014.6850680
  6. 6.
    Renals S, Swietojanski P (2014) Neural networks for distant speech recognition. In: 2014 4th joint workshop on hands-free speech communication and microphone arrays (HSCMA), 12–14 May 2014.  https://doi.org/10.1109/hscma.2014.6843274
  7. 7.
    Zainuddin Z, Pauline O (2007) Function approximation using artificial neural networks. Int J Syst Appl Eng Dev 1(4)Google Scholar
  8. 8.
    Wang G, Guo L, Duan H (2013) Wavelet neural network using multiple wavelet functions in target threat assessment. Sci World J 2013 (Article ID 632437)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • John Sahaya Rani Alex
    • 1
  • Arka Das
    • 2
  • Suhit Atul Kodgule
    • 2
  • Nithya Venkatesan
    • 2
  1. 1.School of Electronics EngineeringVIT UniversityChennaiIndia
  2. 2.School of Electrical EngineeringVIT UniversityChennaiIndia

Personalised recommendations