Abstract
Nowadays, automatic speech emotion recognition has numerous applications. One of the important steps of these systems is the feature selection step. Because it is not known which acoustic features of person’s speech are related to speech emotion, much effort has been made to introduce several acoustic features. However, since employing all of these features will lower the learning efficiency of classifiers, it is necessary to select some features. Moreover, when there are several speakers, choosing speaker-independent features is required. For this reason, the present paper attempts to select features which are not only related to the emotion of speech, but are also speaker-independent. For this purpose, the current study proposes a multi-task approach which selects the proper speaker-independent features for each pair of classes. The selected features are then given to the classifier. Finally, the outputs of the classifiers are appropriately combined to achieve an output of a multi-class problem. Simulation results reveal that the proposed approach outperforms other methods and offers higher efficiency in terms of detection accuracy and runtime.
Similar content being viewed by others
References
Argyriou A, Evgeniou T, Pontil M (2007) Multi-task feature learning. In: Advances in neural information processing systems, pp 41–48
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imaging Sci 2(1):183–202
Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B (2005) A database of German emotional speech. In: Ninth European Conference on Speech Communication and Technology, pp 1516–1520
Charoendee M, Suchato A, Punyabukkana P (2017) Speech emotion recognition using derived features from speech segment and kernel principal component analysis. In: Computer Science and Software Engineering (JCSSE), 2017 14th International Joint Conference on IEEE, pp 1–6
Chen L, Wu M, Zhou M, Liu Z, She J, Hirota K (2017) Dynamic emotion understanding in human-robot interaction based on two-layer fuzzy SVR-TS model. IEEE Trans Syst Man Cybern Syst 50(99):1–12
Dang T, Sethu V, Ambikairajah E (2016) Factor analysis based speaker normalisation for continuous emotion prediction. In: INTERSPEECH, pp 913–917
Demircan S, Kahramanli HJNC, Applications, (2018) Application of fuzzy C-means clustering algorithm to spectral features for emotion classification from speech. Neural Comput Appl 29(8):59–66
Dibeklioğlu H, Hammal Z, Cohn JF (2018) Dynamic multimodal measurement of depression severity using deep autoencoding. IEEE J Biomed Health Inf 22(2):525–536
Escalera S, Pujol O, Radeva P (2010) On the decoding process in ternary error-correcting output codes. IEEE Trans Pattern Anal Mach Intell 32(1):120–134
Eyben F, Wöllmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on Multimedia. ACM, New York, pp 1459–1462
Farrús M, Ejarque P, Temko A, Hernando J (2007) Histogram equalization in svm multimodal person verification. In: International Conference on Biometrics. Springer, Berlin, pp 819–827
Fredrickson BL (2001) The role of positive emotions in positive psychology: The broaden-and-build theory of positive emotions. Am Psychol 56(3):218
Fu J, Mao Q, Tu J, Zhan Y (2019) Multimodal shared features learning for emotion recognition by enhanced sparse local discriminative canonical correlation analysis. Multimed Syst 25(5):451–461
Fürnkranz J (2002) Round robin classification. J Mach Learn Res 2(Mar):721–747
Gajsek R, Štruc V, Mihelič F (2010) Multi-modal emotion recognition using canonical correlations and acoustic features. In: 2010 20th International Conference on Pattern Recognition. IEEE, pp 4133–4136
Gao L, Qi L, Chen E, Guan L (2014) A fisher discriminant framework based on Kernel Entropy Component Analysis for feature extraction and emotion recognition. In: 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) IEEE, pp 1–6
Jin Y, Song P, Zheng W, Zhao L (2014) A feature selection and feature fusion combination method for speaker-independent speech emotion recognition. In: Acoustics, Speech and Signal Processing (ICASSP) (2014) IEEE International Conference on. IEEE, pp 4808–4812
Kaya H, Karpov AA (2018) Efficient and effective strategies for cross-corpus acoustic emotion recognition. Neurocomputing 275:1028–1034
Kaya H, Eyben F, Salah AA, Schuller B (2014) CCA based feature selection with application to continuous depression recognition from acoustic speech features. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) IEEE, pp 3729–3733
Kok BE, Coffey KA, Cohn MA, Catalino LI, Vacharkulksemsuk T, Algoe SB, Brantley M, Fredrickson BL (2016) How positive emotions build physical health: Perceived positive social connections account for the upward spiral between positive emotions and vagal tone: Corrigendum. Psychol Sci 27(6):931
Kotti M, Paternò F (2012) Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema. Int J Speech Technol 15(2):131–150
Kotti M, Paterno F, Kotropoulos C (2010) Speaker-independent negative emotion recognition. In: 2010 2nd International Workshop on Cognitive Information Processing IEEE, pp 417–422
Liu J, Ji S, Ye J (2012) Multi-task feature learning via efficient l2, 1-norm minimization. Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp 339–338
Liu Z-T, Xie Q, Wu M, Cao W-H, Mei Y, Mao J-W (2018) Speech emotion recognition based on an improved brain emotion learning model. Neurocomputing 309:145–156
Liu Z-T, Wu M, Cao W-H, Mao J-W, Xu J-P, Tan G-Z (2018) Speech emotion recognition based on feature selection and extreme learning machine decision tree. Neurocomputing 273:271–280
Lugger M, Yang B (2007) The relevance of voice quality features in speaker independent emotion recognition. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP’07, IEEE, pp 17–20
Martin O, Kotsia I, Macq B, Pitas I (2006) The enterface’05 audio-visual emotion database. In: Data Engineering Workshops (2006) Proceedings. 22nd International Conference on, IEEE, pp 8–8
Nemirovskii A, Nesterov Y (1994) Interior point polynomial algorithms in convex programming. SIAM 36(4):682–683
Nicolaou MA, Panagakis Y, Zafeiriou S, Pantic M (2014) Robust canonical correlation analysis: Audio-visual fusion for learning continuous interest. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) IEEE, pp 1522–1526
Obozinski G, Taskar B, Jordan M (2006) Multi-task feature selection. Statistics Department, Berkeley UC, Tech Rep 2 (2.2):2
Poria S, Cambria E, Bajpai R, Hussain A (2017) A review of affective computing: From unimodal analysis to multimodal fusion. Inf Fusion 37:98–125
Rottenberg J (2017) Emotions in depression: What do we really know? Annu Rev Clin Psychol 13:241–263
Sarvestani RR, Boostani R (2017) FF-SKPCCA: Kernel probabilistic canonical correlation analysis. Appl Intell 46(2):438–454
Schuller B, Vlasenko B, Eyben F, Wollmer M, Stuhlsatz A, Wendemuth A, Rigoll G (2010) Cross-corpus acoustic emotion recognition: Variances and strategies. IEEE Trans Affect Comput 1(2):119–131
Shi C, Ruan Q, An G, Zhao R (2014) Hessian semi-supervised sparse feature selection based on L2, 1/2 -matrix norm. IEEE Trans Multimed 17(1):16–28
Shirani A, Nilchi ARN (2016) Speech emotion recognition based on SVM as both feature selector and classifier. Int J Image Graph Sig Process 8(4):39–45
Song X, Zhang J, Han Y, Jiang J (2016) Semi-supervised feature selection via hierarchical regression for web image classification. Multimed Syst 22(1):41–49
Tang J, Liu H (2012) Unsupervised feature selection for linked social media data. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, New York, pp 904–912
Xie Z, Guan L (2013) Multimodal information fusion of audio emotion recognition based on kernel entropy component analysis. Int J Semant Comput 7(01):25–42
Xu X, Huang C, Wu C, Zhao L (2016) Locally discriminant diffusion projection and its application in speech emotion recognition. Automatika 57(1):37–45
Yaacob S, Muthusamy H, Polat K (2015) Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals. PLoS One 10(3):1–20
Yang B, Lugger M (2010) Emotion recognition from speech signals using new harmony features. Signal Process 90(5):1415–1423
Yang N, Yuan J, Zhou Y, Demirkol I, Duan Z, Heinzelman W, Sturge-Apple M (2017) Enhanced multiclass SVM with thresholding fusion for speech-based emotion classification. Int J Speech Technol 20(1):27–41
Yang X, Garcia KM, Jung Y, Whitlow CT, McRae K, Waugh CE (2018) vmPFC activation during a stressor predicts positive emotions during stress recovery. Soc Cognit Affect Neurosci 13(3):256–268
Yeh Y-c, Lai G-J, Lin CF, Lin C-W, Sun H-C (2015) How stress influences creativity in game-based situations: Analysis of stress hormones, negative emotions, and working memory. Comput Educ 81:143–153
Yogesh C, Hariharan M, Ngadiran R, Adom AH, Yaacob S, Polat K (2017) Hybrid BBO_PSO and higher order spectral features for emotion and stress recognition from natural speech. Appl Soft Comput 56:217–232
Yogesh C, Hariharan M, Yuvaraj R, Ngadiran R, Yaacob S, Polat K (2017) Bispectral features and mean shift clustering for stress and emotion recognition from natural speech. Comput Electr Eng 62(2):676–691
Yogesh C, Hariharan M, Ngadiran R, Adom AH, Yaacob S, Berkai C, Polat K (2017) A new hybrid PSO assisted biogeography-based optimization for emotion and stress recognition from speech signal. Expert Syst Appl 69(1):149–158
Zhang S, Zhao X, Lei B (2013) Speech emotion recognition using an enhanced kernel isomap for human-robot interaction. Int J Adv Rob Syst 10(2):114
Zhang B, Provost EM, Essl G (2016) Cross-corpus acoustic emotion recognition from singing and speaking: A multi-task learning approach. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Piscataway, pp 5805–5809
Zhang B, Provost EM, Essl G (2017) Cross-corpus acoustic emotion recognition with multi-task learning: Seeking common ground while preserving differences. IEEE Trans Affect Comput 10(1):85–99
Zhou J, Chen J, Ye J (2011) Malsar: Multi-task learning via structural regularization. Arizona State University, Tempe, 21
Zou D, Wang J (2015) Speech recognition using locality preserving projection based on multi kernel learning supervision. In: 2015 International Symposium on Computers & Informatics, vol 2352-538X. Atlantis Press, Amsterdam, pp 1508–1516
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no potential conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kalhor, E., Bakhtiari, B. Speaker independent feature selection for speech emotion recognition: A multi-task approach. Multimed Tools Appl 80, 8127–8146 (2021). https://doi.org/10.1007/s11042-020-10119-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10119-w