Skip to main content
Springer Nature Link
Log in

Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The speech signal consists of linguistic information and also paralinguistic one such as emotion. The modern automatic speech recognition systems have achieved high performance in neutral style speech recognition, but they cannot maintain their high recognition rate for spontaneous speech. So, emotion recognition is an important step toward emotional speech recognition. The accuracy of an emotion recognition system is dependent on different factors such as the type and number of emotional states and selected features, and also the type of classifier. In this paper, a modular neural-support vector machine (SVM) classifier is proposed, and its performance in emotion recognition is compared to Gaussian mixture model, multi-layer perceptron neural network, and C5.0-based classifiers. The most efficient features are also selected by using the analysis of variations method. It is noted that the proposed modular scheme is achieved through a comparative study of different features and characteristics of an individual emotional state with the aim of improving the recognition performance. Empirical results show that even by discarding 22% of features, the average emotion recognition accuracy can be improved by 2.2%. Also, the proposed modular neural-SVM classifier improves the recognition accuracy at least by 8% as compared to the simulated monolithic classifiers.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Bosch L (2003) Emotions, speech and the ASR framework. Speech Commun 40:213–225

    Article  MATH  Google Scholar 

  2. Albornoz EM, Milone DH, Rufiner HL (2011) Spoken emotion recognition using hierarchical classifiers. Comput Speech Lang 25:556–570

    Article  Google Scholar 

  3. Ai H, Litman DJ, Forbes-Riley K, Rotaru M, Tetreault J, Purandare A (2006) Using system and user performance features to improve emotion detection in spoken tutoring systems. In: The proceedings of Interspeech, pp 797–800

  4. Devillers L, Vidrascu L (2006) Real-life emotions detection with lexical and paralinguistic cues on human–human call center dialogs. In: The proceedings of Interspeech, pp 801–804

  5. Lee CC, Mower E, Busso C, Lee S, Narayanan S (2009) Emotion recognition using a hierarchical binary decision tree approach. In: The proceedings of Interspeech, pp 320–323

  6. Polzehl T, Sundaram S, Ketabdar H, Wagner M, Metze F (2009) Emotion classification in children’s speech using fusion of acoustic and linguistic features. In: The proceedings of Interspeech, pp 340–343

  7. Klein J, Moon Y, Picard RW (2002) This computer responds to user frustration: theory, design and results. Interact Comput 14:119–140

    Article  Google Scholar 

  8. López-Cózar R, Silovsky J, Kroul M (2011) Enhancement of emotion detection in spoken dialogue systems by combining several information sources. Speech Commun 53:1210–1228

    Article  Google Scholar 

  9. Fernandez R, Picard R (2011) Recognizing affect from speech prosody using hierarchical graphical models. Speech Commun 53:1088–1103

    Article  Google Scholar 

  10. Oudeyer PY (2003) The production and recognition of emotions in speech: features and algorithms. Int J Hum Comput Interact Stud 59:157–183

    Article  Google Scholar 

  11. Huber R, Batliner A, Buckow J, Nöth E, Warnke V, Niemann H (2000) Recognition of emotion in a realistic dialogue scenario. In: The proceedings of international conference on spoken language processing, pp 665–668

  12. Yacoub S, Simske S, Lin X, Burns J (2003) Recognition of emotions in interactive voice response systems. In: The proceeding of European conference on speech communication and technology, pp 729–732

  13. Polzehl T, Schmitt A, Metze F, Wagner M (2011) Anger recognition in speech using acoustic and linguistic cues. Speech Commun 53:1198–1209

    Article  Google Scholar 

  14. Lee CM, Narayanan S (2003) Emotion recognition using a data-driven fuzzy inference system. In: The proceedings of Eurospeech, pp 157–160

  15. Litman DJ, Forbes-Riley K (2006) Recognizing student emotions and attitudes on the basis of utterances in spoken tutoring dialogues with both human and computer tutors. Speech Commun 48:559–590

    Article  Google Scholar 

  16. Batliner A, Fischer K, Huber R, Spilker J, Nöth E (2003) How to find trouble in communication. Speech Commun 40:117–143

    Article  MATH  Google Scholar 

  17. Ang J, Dhillon R, Krupski A, Shriberg E, Stolcke A (2002) Prosody-based automatic detection of annoyance and frustration in human-computer dialog. In: The proceedings of international conference on spoken language processing, pp 2037–2039

  18. Liscombe J, Hirschberg J, Venditti JJ (2005) Detecting certainness in spoken tutorial dialogues. In: The proceeding of European conference on speech communication and technology, pp 1837–1840

  19. Womack BD, Hansen JHL (1996) Classification of speech under stress using target driven features. Speech Commun 20:131–150

    Article  Google Scholar 

  20. Gharavian D, Ahadi SM (2008) Stressed speech recognition using a warped frequency scale. IEICE Electron Express 5:187–191

    Article  Google Scholar 

  21. Laukka P, Neiberg D, Forsell M, Karlsson I, Elenius K (2011) Expression of affect in spontaneous speech: acoustic correlates and automatic detection of irritation and resignation. Comput Speech Lang 25:84–104

    Article  Google Scholar 

  22. Tolkmitt FJ, Scherer KR (1986) Effect of experimentally induced stress on vocal parameters. J Exp Psychol Hum Percept Perform 12:302–313

    Article  Google Scholar 

  23. Cairns D, Hansen JHL (1994) Nonlinear analysis and detection of speech under stressed conditions. J Acoust Soc Am 96:3392–3400

    Article  Google Scholar 

  24. Dellaert F, Polzin T, Waibel A (1996) Recognizing emotion in speech. In: The proceedings of international conference on spoken language processing, vol 3, pp 1970–1973

  25. Lee CM, Narayanan SS (2005) Toward detecting emotions in spoken dialogs. IEEE Trans Speech Audio Process 13:293–303

    Article  Google Scholar 

  26. Gharavian D, Ahadi SM (2005) The effect of emotion on Farsi speech parameters: a statistical evaluation. In: The proceedings of international conference on speech and computer, pp 463–466

  27. Ververidis D, Kotropoulos C (2006) Emotional speech recognition: resources, features, and methods. Speech Commun 48:1162–1181

    Article  Google Scholar 

  28. Shami M, Verhelst W (2007) An evaluation of the robustness of existing supervised machine learning approaches to the classifications of emotions in speech. Speech Commun 49:201–212

    Article  Google Scholar 

  29. Altun H, Polat G (2009) Boosting selection of speech related features to improve performance of multi-class SVMs in emotion detection. Expert Syst Appl 36:8197–8203

    Article  Google Scholar 

  30. Gharavian D, Sheikhan M, Nazerieh AR, Garoucy S (2011) Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network. Neural Comput Appl (published online 27 May 2011). doi:10.1007/s00521-011-0643-1

  31. Sheikhan M, Safdarkhani MK, Gharavian D (2011) Emotion recognition of speech using small-size selected feature set and ANN-based classifiers: a comparative study. World Appl Sci J 14:616–625

    Google Scholar 

  32. Gharavian D, Sheikhan M, Pezhmanpour M (2011) GMM-based emotion recognition in Farsi language using feature selection algorithms. World Appl Sci J 14:626–638

    Google Scholar 

  33. Fersini E, Messina E, Archetti F (2012) Emotional states in judicial courtrooms: an experimental investigation. Speech Commun 54:11–22

    Article  Google Scholar 

  34. Young SJ, Evermann G, Kershaw D, Moore G, Odell J, Ollason D, Povey D, Valtchev V, Woodland P (2002) The HTK book (Ver. 3.2). Cambridge University Press, Cambridge

    Google Scholar 

  35. SPSS Inc. (2007) Clementine® 12.0 algorithms guide. Integral Solutions Limited, Chicago

  36. Freedman DA (2005) Statistical models: theory and practice. Cambridge University Press, Cambridge

    Book  Google Scholar 

  37. Rong J, Li G, Chen YP (2009) Acoustic feature selection for automatic emotion recognition from speech. Info Process Manage 45:315–328

    Article  Google Scholar 

  38. Kao Y, Lee L (2006) Feature analysis for emotion recognition from Mandarin speech considering the special characteristics of Chinese language. In: The proceedings of international conference on spoken language processing, pp 1814–1817

  39. Neiberg D, Elenius K, Laskowski K (2006) Emotion recognition in spontaneous speech using GMMs. In: The proceedings of international conference on spoken language processing, pp 809–812

  40. Pao T, Chen Y, Yeh J, Chang Y (2008) Emotion recognition and evaluation of Mandarin speech using weighted D-KNN classification. Int J Innov Comput Info Control 4:1695–1709

    Google Scholar 

  41. Sidorova J (2009) Speech emotion recognition with TGI+.2 classifier. In: The proceedings of the EACL student research workshop, pp 54–60

  42. Gajšek R, Štruc V, Mihelič F (2010) Multi-modal emotion recognition using canonical correlations and acoustic features. In: The proceedings of international conference on pattern recognition, pp 4133–4136

  43. Yang B, Lugger M (2010) Emotion recognition from speech signals using new harmony features. Signal Process 90:1415–1423

    Article  MATH  Google Scholar 

  44. Bitouk D, Verma R, Nenkova A (2010) Class-level spectral features for emotion recognition. Speech Commun 52:613–625

    Article  Google Scholar 

  45. Yeh J, Pao T, Lin C, Tsai Y, Chen Y (2010) Segment-based emotion recognition from continuous Mandarin Chinese speech. Comput Hum Behav 27:1545–1552

    Article  Google Scholar 

  46. Wu S, Falk TH, Chan WY (2011) Automatic speech emotion recognition using modulation spectral features. Speech Commun 53:768–785

    Article  Google Scholar 

  47. He L, Lech M, Maddage NC, Allen NB (2011) Study of empirical mode decomposition and spectral analysis for stress and emotion classification in natural speech. Biomed Signal Process Control 6:139–146

    Article  Google Scholar 

  48. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97:273–324

    Article  MATH  Google Scholar 

  49. Hyvarinen A (1999) Survey of independent component analysis. Neural Comput Surv 2:94–128

    Google Scholar 

  50. Talavera L (1999) Feature selection as a preprocessing step for hierarchical clustering. In: The proceedings of international conference on machine learning, pp 389–397

  51. Liu H, Motoda H, Yu L (2002) Feature selection with selective sampling. In: The proceedings of international conference on machine learning, pp 395–402

  52. Ververidis D, Kotropoulos C (2006) Fast sequential floating forward selection applied to emotional speech features estimated on DES and SUSAS data collections. In: The proceedings of European signal processing conference, pp 1–5

  53. Batliner A, Steidl S, Schuller B, Seppi D, Vogt T, Wagner J, Devillers L, Vidrascu L, Aharonson V, Kessous L, Amir N (2011) Whodunnit-Searching for the most important feature types signalling emotion-related user states in speech. Comput Speech Lang 25:4–28

    Article  Google Scholar 

  54. Haq S, Jackson PJB, Edge J (2008) Audio-visual feature selection and reduction for emotion classification. In: The proceedings of international conference on auditory-visual speech processing, pp 185–190

  55. Pérez-Espinosa H, Reyes-García CA, Villaseñor-Pineda L (2011) Acoustic feature selection and classification of emotions in speech using a 3D continuous emotion model. Biomed Signal Process Control (published online 3 April 2011). doi:10.1016/j.bspc.2011.02.008

  56. Petrushin VA (2000) Emotion recognition in speech signal: experimental study, development, and application. In: The proceedings of the international conference on spoken language processing, pp 222–225

  57. Väyrynen E, Toivanen J, Seppänen T (2011) Classification of emotion in spoken Finnish using vowel-length segments: increasing reliability with a fusion technique. Speech Commun 53:269–282

    Article  Google Scholar 

  58. Iliev AI, Scordilis MS, Papa JP, Falcão AX (2010) Spoken emotion recognition through optimum-path forest classification using glottal features. Comput Speech Lang 24:445–460

    Article  Google Scholar 

  59. El Ayadi M, Kamel MS, Karray F (2011) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recognit 44:572–587

    Article  MATH  Google Scholar 

  60. Nwe TL, Foo SV, De Silva LC (2003) Speech emotion recognition using hidden Markov models. Speech Commun 41:603–623

    Article  Google Scholar 

  61. Schuller B, Rigoll G, Lang M (2003) Hidden Markov model-based speech emotion recognition. In: The proceedings of the international conference on acoustics, speech, and signal processing, vol 2, pp 1–4

  62. Luengo I, Navas E, Hernáez I, Sanchez J (2005) Automatic emotion recognition using prosodic parameters. In: The proceeding of Interspeech, pp 493–496

  63. Kockmann M, Burget L, Černocky JH (2011) Application of speaker- and language identification state-of-the-art techniques for emotion recognition. Speech Commun (article in press). doi:10.1016/j.specom.2011.01.007

  64. Schuller B, Rigoll G, Lang M (2004) Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. In: The proceedings of the international conference on acoustics, speech, and signal processing, vol 1, pp 577–580

  65. Chuang ZJ, Wu CH (2004) Emotion recognition using acoustic features and textual content. In: The proceedings of the international conference on multimedia and expo, vol 1, pp 53–56

  66. Hoch S, Althoff F, McGlaun G, Rigooll G (2005) Bimodal fusion of emotional data in an automotive environment. In: The proceedings of the international conference on acoustics, speech, and signal processing, vol 2, pp 1085–1088

  67. Morrison D, Wang R, de Silva LC (2007) Ensemble methods for spoken emotion recognition in call-centers. Speech Commun 49:98–112

    Article  Google Scholar 

  68. Chandaka S, Chatterjee A, Munshi S (2009) Support vector machines employing cross-correlation for emotional speech recognition. Measurement 42:611–618

    Article  Google Scholar 

  69. Wang F, Verhelst W, Sahli H (2011) Relevance vector machine based speech emotion recognition. Lecture Notes in Computer Science. Affect Comput Intell Interact 6975:111–120

    Article  Google Scholar 

  70. Nicholson J, Takahashi K, Nakatsu R (1999) Emotion recognition in speech using neural networks. In: The proceedings of the international conference on neural information processing, vol 2, pp 495–501

  71. Lee CM, Narayanan S, Pieraccini R (2002) Combining acoustic and language information for emotion recognition. In: The proceedings of the international conference on spoken language processing, pp 873-876

  72. Park CH, Lee DW, Sim KB (2002) Emotion recognition of speech based on RNN. In: The proceedings of the international conference on machine learning and cybernetics, vol 4, pp 2210–2213

  73. Caridakis G, Karpouzis K, Kollias S (2008) User and context adaptive neural networks for emotion recognition. Neurocomputing 71:2553–2562

    Article  Google Scholar 

  74. Planet S, Iriondo I, Socor′o J, Monzo C, Adell J (2009) GTMURL contribution to the INTERSPEECH 2009 emotion challenge. In: The proceedings of 10th annual of the international speech communication association (Interspeech’09), pp 316–319

  75. Lee CC, Mower E, Busso C, Lee S, Narayanan S (2011) Emotion recognition using a hierarchical binary decision tree approach. Speech Commun 53:1162–1171

    Article  Google Scholar 

  76. Schwenker F, Scherer S, Schmidt M, Schels M, Glodek M (2010) Multiple classifier systems for the recognition of human emotions. Lecture Notes in Computer Science. Multiple Classif Syst 5997:315–324

    Article  Google Scholar 

  77. Schwenker F, Scherer S, Magdi YM, Palm G (2009) The GMM-SVM supervector approach for the recognition of the emotional status from speech. Lecture Notes in Computer Science. Artif Neural Netw 5768:894–903

    Google Scholar 

  78. Scherer S, Schwenker F, Palm G (2008) Emotion recognition from speech using multi-classifier systems and RBF-ensembles. Studies in Computational Intelligence. Speech, audio, image and biomedical signal processing using neural networks, vol 83, pp 49–70

  79. Wu CH, Liang WB (2011) Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Trans Affect Comput 2:10–21

    Article  Google Scholar 

  80. Lefter I, Rothkrantz LJM, Wiggers P, van Leeuwen DA (2010) Emotion recognition from speech by combining databases and fusion of classifiers. Lecture Notes in Computer Science. Text Speech Dialogue 6231:353–360

    Article  Google Scholar 

  81. Scherer S, Schwenker F, Palm G (2009) Classifier fusion for emotion recognition from speech. In: Advanced intelligent environments, pp 95–117

  82. Pao TL, Chien CS, Chen YT, Yeh JH, Cheng YM, Liao WY (2007) Combination of multiple classifiers for improving emotion recognition in Mandarin speech. In: The proceedings of the international conference on intelligent information hiding and multimedia signal processing, vol 1, pp 35–38

  83. Clavel C, Vasilescu I, Devillers L (2011) Fiction support for realistic portrayals of fear-type emotional manifestations. Comput Speech Lang 25:63–83

    Article  Google Scholar 

  84. Bijankhan M, Sheikhzadegan J, Roohani MR, Samareh Y, Lucas C, Tebiani M (1994) The speech database of Farsi spoken language. In: The proceedings of the international conference on speech science and technology, pp 826–831

  85. Schuller B, Batliner A, Steidl S, Seppi D (2011) Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Commun (article in press). doi:10.1016/j.specom.2011.01.011

  86. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182

    MATH  Google Scholar 

  87. Hochberg Y, Tamhane AC (1987) Multiple comparison procedures. Wiley, New York

    Book  MATH  Google Scholar 

  88. NIST/SEMATECH (2011) e-Handbook of statistical methods. (http://www.itl.nist.gov/div898/handbook/)

  89. Hastie T, Tibshirani R (1998) Classification by pairwise coupling. Ann Stat 26:451–471

    Article  MathSciNet  MATH  Google Scholar 

  90. Ghanem AS, Venkatesh S, West G (2010) Multi-class pattern classification in imbalanced data. In: The proceedings of the international conference on pattern recognition, pp 2881–2884

  91. Wang Y, Guan L (2005) Recognizing human emotion from audiovisual information. In: The proceedings of the international conference on acoustics, speech, and signal processing, pp 1125–1128

  92. Kittler J, Hojjatoleslami A, Windeatt T (1997) Weighting factors in multiple expert fusion. In: The proceedings of the British machine vision conference, pp 42–50

  93. Yu F, Chang E, Xu Y, Shum H (2001) Emotion detection from speech to enrich multimedia content. In: The proceedings of the IEEE Pacific Rim conference on multimedia: advances in multimedia information processing, pp 550–557

  94. Kwon OW, Chan K, Hao J, Lee TW (2003) Emotion recognition by speech signal. In: The proceedings of the European conference on speech communication and technology, pp 125–128

  95. Ayadi M, Kamel S, Karray F (2007) Speech emotion recognition using Gaussian mixture vector autoregressive models. In: The proceedings of the international conference on acoustics, speech, and signal processing, vol 5, pp 957–960

Download references

Author information

Authors and Affiliations

  1. EE Department, Faculty of Engineering, Islamic Azad University, South Tehran Branch, P.O. Box: 11365-4435, Tehran, Iran

    Mansour Sheikhan & Mahdi Bejani

  2. EE Department, Shahid Abbaspour University of Technology, Tehran, Iran

    Davood Gharavian

Authors
  1. Mansour Sheikhan
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mahdi Bejani
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Davood Gharavian
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mansour Sheikhan.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sheikhan, M., Bejani, M. & Gharavian, D. Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method. Neural Comput & Applic 23, 215–227 (2013). https://doi.org/10.1007/s00521-012-0814-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-0814-8

Keywords