Neural Network Configurations Analysis for Identification of Speech Pattern with Low Order Parameters

  • Priscila Lima
  • Allan Barros
  • Washington Silva
Conference paper
Part of the Studies in Computational Intelligence book series (SCI, volume 751)


This work proposes the analysis between two neural network configurations for development a intelligent recognition system of speech signal patterns of numerical commands in Brazilian Portuguese. Thus, the Multilayer Perceptron (MLP) and Learning Vector Quantization (LVQ) networks are evaluated their performance in the course of training, validation and testing in speech signal recognition, whose pattern of speech signal is given by a two-dimensional time matrix, resulting of the encoding of the mel-cepstral coefficients (MFCC) through application of discrete cosine transform (DCT). These patterns have reduced set of parameters and the configurations of neural network in analysis use few examples for each pattern through training. It was carried out many simulations for network topologies and some selected learning algorithms to determine the network structures with best hit and generalization results. The potential this proposed approach is shown by check up on obtained outcomes with others classifiers, represented by Gaussian Mixture Models (GMM) and Support Vector Machines (SVM).


  1. 1.
    Petry, F.E.: Speech recognition: a current perspective: in spite of limitations, areas of application are growing, and voice communication with computers may well be commonplace by the 21st century. IEEE Potentials 2, 18–20 (1983).
  2. 2.
    Husnjak, S., Perakovic, D., Jovovic, I.: Possibilities of using speech recognition systems of smart terminal devices in traffic environment. Proc. Eng. 69, 778–787 (2014)CrossRefGoogle Scholar
  3. 3.
    Špale, J., Schweize, C.: Speech control of measurement devices. IFAC-PapersOnLine 49, 13–18 (2016).
  4. 4.
    Breen, A., et al.: Voice in the user interface. In: Interactive Displays: Natural Human-Interface Technologies. (2014)
  5. 5.
    Bisio, I., et al.: Gender-driven emotion recognition through speech signals for ambient intelligence applications. IEEE Trans. Emerg. Top. Comput. 1, 244–257 (2013).
  6. 6.
    Weng, F., et al.: Conversational in-vehicle dialog systems: the past, present, and future. IEEE Signal Process. Mag. 33, 49–60 (2016).
  7. 7.
    Yang, Y., Li, L.: The design and implementation of a smart e-receptionist. IEEE Potentials 32, 22–27 (2013).
  8. 8.
    Singh, T., Yadav, N.: Voice recognition based advance patient’s room automation. IJRET: Int. J. Res. Eng. Technol. 4, 308–310 (2015)Google Scholar
  9. 9.
    Silva, W.L.S.: Intelligent genetic fuzzy inference system for speech recognition: an approach from low order feature based on discrete cosine transform. J. Control Autom. Electr. Syst. 25, 689–698 (2014)CrossRefGoogle Scholar
  10. 10.
    Bellegarda, J.R., Monz, C.: State of the art in statistical methods for language and speech processing. Comput. Speech Lang. 35, 163–184 (2016).
  11. 11.
    Youcef, B.C.: Speech recognition system based on OLLO French corpus by using MFCCs. In: Lecture Notes in Electrical Engineering. (2017)
  12. 12.
    Sarma, M., Sarma, K.K.: Acoustic modeling of speech signal using artificial neural network: a review of techniques and current trends. In: Intelligent Applications for Heterogeneous System Modeling and Design. (2015)
  13. 13.
    Lee, C.H., Siniscalchi, S.M.: An information-extraction approach to speech processing: analysis, detection, verification, and recognition. Proc. IEEE 101, 1089–1115 (2013).
  14. 14.
    O’Shaughnessy, D.: Acoustic analysis for automatic speech recognition. Proc. IEEE 101, 1038–1053 (2013).
  15. 15.
    Silva, W.: Sistema de Inferência Genética-Nebuloso para Reconhecimento de Voz (System of fuzzy- genetic inference for speech recognition) Thesis, Federal University of Maranhão (2015)Google Scholar
  16. 16.
    Bridle, J.S.: Neural networks or hidden markov models for automatic speech recognition: is there a choice? In: Pietro, L., De Mori, R. (eds.) Speech Recognition and Understanding: Recent Advances, Trends and Applications, vol. 75, pp. 225–236. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  17. 17.
    McCrocklin, S.M.: Pronunciation learner autonomy: the potential of automatic speech recognition. System 57, 25–42 (2016).
  18. 18.
    Picheny, M.: Trends and advances in speech recognition. IBM J. Res. Dev. 55, 1–18 (2011).
  19. 19.
    Haton, J.P.: Neural networks for automatic speech recognition: a review. In: Chollet, G., et al. (eds.) Speech Processing, Recognition and Artificial Neural Networks: Proceedings of the 3rd International School on Neural Nets “Eduardo R. Caianiello”, 1999, pp. 259–280. Springer, London (1999)Google Scholar
  20. 20.
    Nightingale, C., Myers, D.J., Linggard, R.: Introduction neural networks for vision, speech and natural language. In: Nightingale, C., Myers, D.J., Linggard, R. (eds.) Neural Networks for Vision, Speech and Natural Language, vol. 1, pp. 1–4. Springer, Netherlands (1992)Google Scholar
  21. 21.
    Siniscalchi, S.M., Svendsen, T., Lee, C.-H.: An artificial neural network approach to automatic speech processing. Neurocomputing 140, 326–338 (2014).
  22. 22.
    Lippmann, R.P.: Review of neural networks for speech recognition. Neural Comput. 1, 1–38 (1989).
  23. 23.
    Hu, Y.H., Hwang, J.N. (eds.): Handbook of Neural Networks for Speech Processing. CRC Press, Washington DC (2014)Google Scholar
  24. 24.
    Kim, M.W., Ryu, J.W., Kim, E.J.: Speech recognition with multi-modal features based on neural networks. In: King, I., et al. (eds.) Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October, 2006. Proceedings, Part II. Lecture Notes in Computer Science (Lecture Notes in Neural Information Processing), vol. 4233, pp. 489–498. Springer, Heidelberg (2006)Google Scholar
  25. 25.
    Veselý, K., Burget, L., Grézl, F.: Parallel training of neural networks for speech recognition. In: Sojka, P., et al. (eds.) Text, Speech and Dialogue: 13th International Conference, TSD 2010, Brno, Czech Republic, Sept 2010. Lecture Notes in Computer Science (Lecture Notes in Text, Speech and Dialogue), vol. 6231. Springer, Heidelberg (2010)Google Scholar
  26. 26.
    Yam, J.Y.F., Chow, T.W.S.: A weight initialization method for improving training speed in feedforward neural network. Neural Comput. 30, 219–232 (2000)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Federal University of MaranhãoSão Luís-MaBrazil
  2. 2.Federal Institute of MaranhãoSão Luís-MaBrazil

Personalised recommendations