Skip to main content
SpringerLink
Log in

Handling high dimensional features by ensemble learning for emotion identification from speech signal

  • Published:
International Journal of Speech Technology Aims and scope Submit manuscript

Abstract

In the recent past, handling the curse of dimensionality observed in acoustic features of the speech signal in machine learning-based emotion detection has been considered a crucial objective. The contemporary emotion prediction methods are experiencing false alarming due to the high dimensionality of the features used in training phase of the machine learning models. The majority of the contemporary models have endeavored to handle the curse of high dimensionality of the training corpus. However, the contemporary models are focusing more on using fusion of multiple classifiers, which is barely improvising the decision accuracy, if the volume of the training corpus is high. The contribution of this manuscript endeavored to portray a novel ensemble model that using fusion of diversity measures to suggest the optimal features. Moreover, the proposed method attempts to reduce the impact of the high dimensionality in feature values by using a novel clustering process. The experimental study signifies the proposed method performance in term of emotion prediction from speech signals and compared to contemporary models of emotion detection using machine learning. The fourfold cross-validation of standard data corpus has used in performance analysis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Abbreviations

SER:

Speech emotion recognition

ML:

Machine learning

MFC:

Mel-frequency cepstral coefficient

LPCC:

Linear predictive cepstral coefficient

PLP:

Perceptual linear prediction

ZCR:

Zero-crossing rate

DNN:

Deep neural network

CWT:

Continuous wavelet transforms

EMD:

Empirical mode decomposition

MS:

Modulation spectral

HAF:

Hybrid acoustic features

DFODM:

Digital feature optimization using fusion of diversity measures

WSR:

Wilcoxon signed-rank

References

  • Alonso, J. B. (2015). New approach in quantification of emotional intensity from the speech signal: Emotional temperature. Expert Systems with Applications, 42(24), 9554–9564.

    Article  Google Scholar 

  • Basu, S. C. (2017). A review on emotion recognition using speech. In 2017 International conference on inventive communication and computational technologies (ICICCT) (pp. 109–114). IEEE.

  • Bhavan, A. C. (2019). Bagged support vector machines for emotion recognition from speech. Knowledge-Based Systems, 184, 104886.

    Article  Google Scholar 

  • Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.

    Article  MATH  Google Scholar 

  • Budak, H. (2016). A modified t-score for feature selection. Anadolu University Journal of Science and Technology A-Applied Sciences and Engineering, 17(5), 845–852.

    Google Scholar 

  • Cao, H. V. (2015). peaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech. Computer Speech & Language, 29(1), 186–202.

    Article  Google Scholar 

  • Cong, P., Wang, C., Ren, Z., Wang, H., Wang, Y., & Feng, J. (2016). Unsatisfied customer call detection with deep learning. In Proceedings of the 2016 10th international symposium on chinese spoken language processing (ISCSLP), 1–5.

  • Dietterich, T. G. (2000). Ensemble methods in machine learning. In International workshop on multiple classifier systems, 1–15.

  • Getahun, F. (2016). Emotion identification from spontaneous communication. In 2016 12th international conference on signal-image technology & internet-based systems (SITIS), 151–158.

  • Ghasemi, A. (2012). Normality tests for statistical analysis: A guide for non-statisticians. International Journal of Endocrinology and Metabolism, 10(2), 486.

    Article  Google Scholar 

  • Hu, Q. H. (2007). Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble. Mechanical Systems and Signal Processing, 21(2), 688–705.

    Article  Google Scholar 

  • Jiang, W. W. (2019). Speech emotion recognition with heterogeneous feature unification of deep neural network. Sensors, 19(12), 2730.

    Article  Google Scholar 

  • K Ashok Kumar, J. L. (2020). Digital feature optimization using fusion of diversity measures for emotion identification from speech signal. Journal of Ambient Intelligence and Humanized Computing, 1–13.

  • Kerkeni, L. S. (2019). Automatic speech emotion recognition using an optimal combination of features based on EMD-TKEO. Speech Communication, 114, 22–35.

    Article  Google Scholar 

  • Khan, A., & Roy, U. (2017). motion recognition using prosodie and spectral features of speech and Naïve Bayes Classifier. In 2017 international conference on wireless communications, signal processing and networking (WiSPNET) (pp. 1017–1021). IEEE.

  • Kim, H. C. (2002). Support vector machine ensemble with bagging. In International workshop on support vector machines, 397–408.

  • Koduru, A., Valiveti, H. B., & Budati, A. K. (2020). Feature extraction algorithms to improve the speech emotion recognition rate. International Journal of Speech Technology, 23(1), 45–55.

    Article  Google Scholar 

  • Liu, F. B. (2016). Boost picking: a universal method on converting supervised classification to semi-supervised classification. arXiv preprint arXiv:abs/1602.05659.

  • Liu, Z. T. (2018). Speech emotion recognition based on feature selection and extreme learning machine decision tree. Neurocomputing, 273, 271–280.

    Article  Google Scholar 

  • Livingstone, S. R. (2018). The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE, 13(5), e0196391.

    Article  Google Scholar 

  • Luengo, I. N. (2010). Feature analysis and evaluation for automatic emotion identification in speech. IEEE Transactions on Multimedia, 12(6), 490–501.

    Article  Google Scholar 

  • Mao, Q. Z. (2011). Extraction and analysis for non-personalized emotion features of speech. Advances in Information Sciences and Service Sciences, 3(10).

  • Matsuki, K. K. (2016). The Random Forests statistical technique: An examination of its value for the study of reading. Scientific Studies of Reading, 20(1), 20–33.

    Article  Google Scholar 

  • McKnight, P. E. (2010). Mann-Whitney U test. The Corsini Encyclopedia of Psychology, 1–1.

  • Moretti, F. P. (2015). Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling. Neurocomputing, 167, 3–7.

    Article  Google Scholar 

  • Morrison, D. W. (2007). Ensemble methods for spoken emotion recognition in call-centres. Speech Communication, 49(2), 98–112.

    Article  Google Scholar 

  • Ozcift, A. (2011). Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms. Computer Methods and Programs in Biomedicine, 104(3), 443–451.

    Article  Google Scholar 

  • Palo, H. K. (2017). Emotion recognition using MLP and GMM for Oriya language. International Journal of Computational Vision and Robotics, 7(4), 426–442.

    Article  MathSciNet  Google Scholar 

  • Pérez-Espinosa, H.R.-G.-P. (2012). Acoustic feature selection and classification of emotions in speech using a 3D continuous emotion model. Biomedical Signal Processing and Control, 7(1), 79–87.

    Article  Google Scholar 

  • pycharm. (n.d.). Retrieved from https://www.jetbrains.com/pycharm/download/: https://www.jetbrains.com/pycharm/download/.

  • Python. (n.d.). Retrieved from https://www.python.org/downloads/; https://www.python.org/downloads/.

  • Quinlan, J. R. (1996). Bagging, boosting, and C4. 5. Aaai/iaai, 1, 725–730.

    Google Scholar 

  • Schapire, R. E. (1990). The strength of weak learnability. Machine Learning, 5(2), 197–227.

    Article  Google Scholar 

  • Schuller, B. R.-H. (2005). Speaker independent speech emotion recognition by ensemble classification. In 2005 IEEE international conference on multimedia and expo (pp. 864–867). IEEE.

  • Semwal, N. K. (2017). Automatic speech emotion detection system using multi-domain acoustic feature selection and classification models. In 2017 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA) (pp. 1–6).

  • Shaqra, F.A.-A. (2019). Recognizing emotion from speech based on age and gender using hierarchical models. Procedia Computer Science, 151, 37–44.

    Article  Google Scholar 

  • Shasidhar, M. R. (2011). MRI brain image segmentation using modified fuzzy c-means clustering algorithm. In 2011 international conference on communication systems and network technologies (pp. 473–478). IEEE.

  • Shegokar, P. &. (2016). Continuous wavelet transform based speech emotion recognition. In 2016 10th international conference on signal processing and communication systems (ICSPCS) (pp. 1–8). IEEE.

  • Stuhlsatz, A. M. (2011). Deep neural networks for acoustic emotion recognition: Raising the benchmarks. In 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5688–5691). IEEE.

  • Stuhlsatz, A., Meyer, C., Eyben, F., Zielke, T., Meier, G., & Schuller, B. (2011). Deep neural networks for acoustic emotion recognition: Raising the benchmarks. In 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5688–5691). IEEE.

  • Sun, L. Z. (2019). Speech emotion recognition based on DNN-decision tree SVM model. Speech Communication, 115, 29–37.

    Article  Google Scholar 

  • Sun, X. (2002). Pitch accent prediction using ensemble machine learning. In Seventh international conference on spoken language processing.

  • Test, F. (n.d.). Retrieved from https://statistics.laerd.com/spss-tutorials/friedman-test-using-spss-statistics.php; https://statistics.laerd.com/spss-tutorials/friedman-test-using-spss-statistics.php.

  • Test, K.-W. (n.d.). Retrieved from https://www.statisticssolutions.com/kruskal-wallis-test/; https://www.statisticssolutions.com/kruskal-wallis-test/.

  • t-table. (2017). Retrieved from http://www.sjsu.edu/faculty/gerstman/StatPrimer/t-table.pdf.

  • van Veen, H. J. (2015). Le Nguyen The Dat Armando Segnini. Kaggle Ensembling Guide. Retrieved from https://mlwave.com/kaggle-ensembling-guide/.

  • Wang, G. H. (2011). A comparative assessment of ensemble learning for credit scoring. Expert Systems with Applications, 38(1), 223–230.

    Article  Google Scholar 

  • wav-to-csv. (n.d.). Retrieved from https://github.com/Lukious/wav-to-csv; https://github.com/Lukious/wav-to-csv.

  • Woolson, R. F. (2007). Wilcoxon signed‐rank test. Wiley encyclopedia of clinical trials, 1–3.

  • Yang, X. S. (2014). Cuckoo search: Recent advances and applications. Neural Computing and Applications, 24(1), 169–174.

    Article  Google Scholar 

  • Yu, Z. Z. (2017). Adaptive semi-supervised classifier ensemble for high dimensional data classification. IEEE Transactions on Cybernetics, 49(2), 366–379.

    Article  Google Scholar 

  • Zareapoor, M. (2015). Application of credit card fraud detection: Based on bagging ensemble classifier. Procedia Computer Science, 48, 679–685.

    Article  Google Scholar 

  • Zhang, Z. C. (2014). Cooperative learning and its application to emotion recognition from speech. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23(1), 15–126.

    Google Scholar 

  • Zvarevashe, K. (2020). Ensemble learning of hybrid acoustic features for speech emotion recognition. Algorithms, 13(3), 70.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Veltech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, India

    Konduru Ashok Kumar

  2. ECE, Institute of Science and Technology, Veltech Rangarajan Dr. Sagunthala R&D, Avadi, Chennai, India

    J. L. Mazher Iqbal

Authors
  1. Konduru Ashok Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. L. Mazher Iqbal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Konduru Ashok Kumar.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ashok Kumar, K., Iqbal, J.L.M. Handling high dimensional features by ensemble learning for emotion identification from speech signal. Int J Speech Technol 25, 837–851 (2022). https://doi.org/10.1007/s10772-021-09916-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10772-021-09916-x

Keywords

Search

Navigation