Advertisement

Cluster Computing

, Volume 22, Supplement 2, pp 3347–3363 | Cite as

Iterative Conditional Entropy Kalman filter (ICEKF) for noise reduction and Neuro Optimized Emotional Classifier (NOEC)

  • R. KumuthaveniEmail author
  • E. Chandra
Article
  • 71 Downloads

Abstract

Emotion has a most important aspect in terms of interactions among the humans and this would become ideal for human emotions to get mechanically identified by the machines and primarily for enhancing the communication among the human–machine. In the recent work Enhanced Bat algorithm with Simulated Annealing (EBSA) are introduced for solving emotion recognition problem. Here the removal of noises from the speech samples and reduction in the number of speech features becomes very difficult task which reduces the accuracy of the classifier. To solve this problem this research work involves detection of emotions from speech which stimulates machines understanding human behavioral tasks namely reasoning, decision making and interaction. EBSA is used in the previous system to identify the happy, sad and neutral emotions from speech input. The performance of the previous system has been decreased due to recognition accuracy and feature selection. Improved Artificial Bee Colony (IABC) with Neuro Optimized Emotional Classifier (NOEC) solves this issue in the proposed system. The Iterative Conditional Entropy Kalman filtering (ICEKF) is initially processed to effectively filter the noisy features from the inputted speech data. Mel Frequency Cepstrum Coefficient (MFCC), pitch, energy, intensity and formants are extracted as speech features. Every extracted feature is maintained in the database and annotated along with their emotional class label. IABC algorithm chooses the feature optimally, which in turn employs the best fitness function values. From the optimally selected dataset, the NOEC is processed. Emotions can be identified from the Tamil news speech dataset with the help of the supervised machine learning technique, which demands the training set (collection of emotional speech recordings). Every recording or sample in the dataset is named with the emotional class and they are indicated as n-dimensional vector of spectrum coefficients which in turn is extracted from the Tamil news speech dataset. This dataset is collected from real time via using the search engine sites like Google, YouTube, twitter etc. By implementing IABC with NOEC classification process, the work segregates the emotional classes such as happy, sad, anger, fear and neutral emotions perfectly. From the experimental verification, it is confirmed that the proposed method IABC with NOEC gives better performances with respect to accuracy, precision, recall and f-measure values.

Keywords

Speech enhancement Feature extraction Feature selection Iterative Conditional Entropy Kalman filtering (ICEKF) Speech emotion recognition Improved Artificial Bee Colony (IABC) algorithm Neuro Optimized Emotional Classifier (NOEC) algorithm 

References

  1. 1.
    Schuller, B., Gerhard, R., Manfred, L.: Hidden Markov model-based speech emotion recognition. Multimed. Expo. ICME’03. In: Proceedings. 2003 International Conference on. vol. 1. IEEE (2003)Google Scholar
  2. 2.
    Schuller, B., Gerhard, R., Manfred, L.: Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. Acoustics, Speech, and Signal Processing, 2004. In: Proceedings.(ICASSP’04). IEEE International Conference on, vol. 1. IEEE (2004)Google Scholar
  3. 3.
    Ingale, A.B., Chaudhari, D.S.: Speech emotion recognition. Int. J. Soft Comput. Eng. (IJSCE) 2(1), 235–238 (2012)Google Scholar
  4. 4.
    Anila, R., Revathy, A.: Emotion recognition using continuous density HMM. Communications and Signal Processing (ICCSP), 2015 International Conference on. IEEE (2015)Google Scholar
  5. 5.
    Martin, Rainer: Speech enhancement based on minimum mean-square error estimation and supergaussian priors. IEEE Trans. Speech Audio Process. 13(5), 845–856 (2005)Google Scholar
  6. 6.
    Tsenov, G.T., Mladenov, V.M.: Speech recognition using neural networks. In: Neural Network Applications in Electrical Engineering (NEUREL), 2010 10th Symposium on. IEEE (2010)Google Scholar
  7. 7.
    You, Chang Huai, Koh, Soo Ngee, Rahardja, S.: Subband Kalman filtering incorporating masking properties for noisy speech signal. Speech Commun. 49(7), 558–573 (2007)Google Scholar
  8. 8.
    Hu, Y., Wu, D., Nucci, A.: Pitch-based gender identification with two-stage classification. Secur. Commun. Netw. 5(2), 211–225 (2012)Google Scholar
  9. 9.
    Yogesh, C.K., et al.: Hybrid BBO_PSO and higher order spectral features for emotion and stress recognition from natural speech. Appl. Soft Comput. 56, 217–232 (2017)Google Scholar
  10. 10.
    Sharan, R.V., Moir, T.J.: Noise robust audio surveillance using reduced spectrogram image feature and one-against-all SVM. Neurocomputing 158, 90–99 (2015)Google Scholar
  11. 11.
    Prasartvit, Thananan, Banharnsakun, Anan, Kaewkamnerdpong, Boonserm, Achalakul, Tiranee: Reducing bio–informatics data dimension with ABC–KNN. Neurocomputing 116, 367–381 (2013)Google Scholar
  12. 12.
    Al-Naser, Mustafa, Elshafei, Moustafa, Al-Sarkhi, Abdelsalam: Artificial neural network application for multiphase flow patterns detection: a new approach. J. Petrol. Sci. Eng. 145, 548–564 (2016)Google Scholar
  13. 13.
    Arai, Kohei: Recovering method of missing data based on proposed improved Kalman filter when time series of mean data is known. Int. J. Adv. Res. Artif. Intell. 2(7), 18–23 (2013)Google Scholar
  14. 14.
    Skoglund, M.A., Hendeby, G., Axehill, D.:Extended Kalman filter modifications based on an optimization view point. 18th International Conference on Information Fusion (Fusion), pp 1856–1861 (2015)Google Scholar
  15. 15.
    Kumuthaveni, R., Chandra, E.: An enhanced bat algorithm with simulated annealing method for speech emotion recognition. Int. J. Adv. Res. Dyn. Control Syst. 1, 125–138 (2017)Google Scholar
  16. 16.
    Chen, J., et al.: Recognition of noisy speech using dynamic spectral subband centroids. IEEE Signal Process. Lett. 11(2), 258–261 (2004)Google Scholar
  17. 17.
    Bozkurt, E., et al.: Formant position based weighted spectral features for emotion recognition. Speech Commun. 53(9), 1186–1197 (2011)Google Scholar
  18. 18.
    Morrison, Donn, Wang, Ruili, de Silva, L.C.: Ensemble methods for spoken emotion recognition in call-centres. Speech Commun. 49(2), 98–112 (2007)Google Scholar
  19. 19.
    Mogaka, L., Murage, D.K., Saulo, M.J.: Rotating Machine based power optimization and prioritization using the artificial bee colony algorithm. In: Proceedings of Sustainable Research and Innovation Conference (2016)Google Scholar
  20. 20.
    Mezura-Montes, Efrén, Cetina-Domínguez, Omar: Empirical analysis of a improved artificial bee colony for constrained numerical optimization. Appl. Math. Comput. 218(22), 10943–10973 (2012)Google Scholar
  21. 21.
    Badri, Lubna: Development of neural networks for noise reduction. Int. Arab J. Inf. Technol. 7(3), 289–294 (2010)Google Scholar
  22. 22.
    Dorronsoro, J., López, V., Cruz, C., Sigüenza, J.: Autoassociative neural networks and noise filtering. IEEE Trans. Signal Process. 51(5), 1431–1438 (2003)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Dr. SNS. Rajalakshmi College of Arts & ScienceCoimbatoreIndia
  2. 2.Department of Computer ScienceBharathiar UniversityCoimbatoreIndia

Personalised recommendations