Abstract
Various models have been proposed with many dimension reduction techniques and classifiers in the field of pattern recognition by using audio signal processing. In this paper, an effective model has been proposed for pattern recognition using PCA as the sole dimension reduction technique and Feed forward Neural network as the classifier. Twenty-eight Parkinson’s disease affected patients’ audio recordings consisting of the pronunciation of the vowels ‘A’ and ‘O’ have been used as the dataset. From these audio recordings twenty features were extracted and PCA was run on those features. PCA rearranged the feature vector matrix in a more optimized manner. Thus the optimal features were arranged in order of their significance. From this rearranged and optimized feature vector matrix, the first eight optimal features were chosen which were later used to train and test the classifier Feed forward Neural network. Experimental results demonstrate that the model can predict the occurrence and pattern of the vowels ‘A’ and ‘O’ from the audio files with very high accuracy compared to the swarm search for feature selection in classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdisc. Rev. Comput. Stat. 2(4), 433–459 (2010). doi:10.1002/wics.101
Asadi, S., Rao, C., Saikrishna, V.: A Comparative study of face recognition with principal component analysis and cross-correlation technique. Int. J. Comput. Appl. 10(8), 17–21 (2010). doi:10.5120/1502-2019
Cybenko, G.: Continuous Valued Neural Networks with Two Hidden Layers are Sufficient, pp. 303–314 (1988)
Fong, S., Yang, X., Deb, S.: Swarm search for feature selection in classification. In: 2013 IEEE 16th International Conference on Computational Science and Engineering (2013). doi:10.1109/cse.2013.135
Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Networks 2(3), 183–192 (1989). doi:10.1016/0893-6080(89)90003-8
Hagan, M.T., Demuth, H.B., Jesús, O.D.: An introduction to the use of neural networks in control systems. Int. J. Robust Nonlinear Control 12(11), 959–985 (2002). doi:10.1002/rnc.727
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989). doi:10.1016/0893-6080(89)90020-8
Howard, W.: Pattern recognition and machine learning. Kybernetes 36(2), 275 (2007). doi:10.1108/03684920710743466. i‐xx, pp. 740. Springer, Heidelberg (2006). ISBN 0‐387‐31073‐8, $74.95 Hardcover
Li, C., Diao, Y., Ma, H., Li, Y.: A statistical PCA method for face recognition. In: 2008 Second International Symposium on Intelligent Information Technology Application (2008). doi:10.1109/iita.2008.71
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989). doi:10.1016/0893-6080(89)90020-8
Mcculloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943). doi:10.1007/bf02478259
Meruelo, A.C., Simpson, D.M., Veres, S.M., Newland, P.L.: Improved system identification using artificial neural networks and analysis of individual differences in responses of an identified neuron. Neural Networks 75, 56–65 (2016). doi:10.1016/j.neunet.2015.12.002
Murali, M.: (2015). Principal component analysis based feature vector extraction. Indian J. Sci. Technol. (2015)
Phillips, P., Flynn, P., Scruggs, T., Bowyer, K., Chang, J., Hoffman, K., Worek, W.: Overview of the Face Recognition Grand Challenge. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005) (2005). doi:10.1109/cvpr.2005.268
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958). doi:10.1037/h0042519
Sakar, B.E., Isenkul, M., Sakar, C.O., Sertbas, A., Gurgen, F., Delil, S., Kursun, O.: Collection and analysis of a parkinson speech dataset with multiple types of sound recordings. IEEE J. Biomed. Health Inform. 17(4), 828–834 (2013). doi:10.1109/jbhi.2013.2245674
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Networks 61, 85–117 (2015). doi:10.1016/j.neunet.2014.09.003
Tamura, S., Tateishi, M.: Capabilities of a four-layered feedforward neural network: four layers versus three. IEEE Trans. Neural Networks 8(2), 251–255 (1997). doi:10.1109/72.557662
Hori, T., Kubo, Y., Nakamura, A.: Real-time one-pass decoding with recurrent neural network language model for speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Momo, N., Abdullah, Uddin, J. (2018). Speech Recognition Using Feed Forward Neural Network and Principle Component Analysis. In: Thampi, S., Krishnan, S., Corchado Rodriguez, J., Das, S., Wozniak, M., Al-Jumeily, D. (eds) Advances in Signal Processing and Intelligent Recognition Systems. SIRS 2017. Advances in Intelligent Systems and Computing, vol 678. Springer, Cham. https://doi.org/10.1007/978-3-319-67934-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-67934-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67933-4
Online ISBN: 978-3-319-67934-1
eBook Packages: EngineeringEngineering (R0)