ESTIMATION OF EMOTIONS NORMAL/ANXIETY BY FUNDAMENTAL FREQUENCY TRAJECTORY ANALYSIS
Keywords:
fundamental frequency, emotion, emotional state, confusion matrixAbstract
In this paper, the emotional state (normal state and anxiety state) of the speaker was detected using speech analysis. In the first part of the paper, an algorithm for evaluating the emotion from the speech is described, which is based on the analysis of the trajectory fundamental frequency F0. At first, the algorithm for determining the criteria, i.e. the decision line, in planes is described (F0, 2) and (F0, T). In the first phase of the training, based on the test signals, the decision criterion for the detection of the emotion (Normal/Anxiety) was defined. The second part of the paper describes an experiment in which a statistical assessment of the accuracy of classifications of the speaker's emotion was performed. In the paper, the confusion matrix was used to evaluate the effectiveness of the emotion assessment (TP, TN, FP, FN and ACC). In order to achieve greater efficiency in the assessment of emotion, the confusion matrix was applied to the results obtained by applying the logical operation on the results obtained in both fields of decision-making. Based on the detection precision parameters, a comparative analysis was performed with the results obtained for the detection of the emotion Normal/Anger. The experimental results are presented tabularly and graphically.
References
Abdul-Hadi, M. H., & Waleed, J. (2020). Human speech and facial emotion recognition technique using SVM. 2020 International Conference on Computer Science and Software Engineering (CSASE). https://doi.org/10.1109/csase48920.2020.9142065.
Akçay, M. B., & Oğuz, K. (2020). Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Communication, 116, 56–76. https://doi.org/10.1016/j.specom.2019.12.001.
Bezooijen, R. (1984). Characteristics and Recognizability of Vocal Expressions of Emotion. Walter de Gruyter.
Cairns, D. A., & Hansen, J. H. (1994). Nonlinear analysis and classification of speech under stressed conditions. The Journal of the Acoustical Society of America, 96(6), 3392–3400. https://doi.org/10.1121/1.410601.
Chul Min Lee, & Narayanan, S. S. (2005). Toward detecting emotions in spoken dialogs. IEEE Transactions on Speech and Audio Processing, 13(2), 293–303. https://doi.org/10.1109/tsa.2004.838534.
El Ayadi, M., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognition, 44(3), 572–587. https://doi.org/10.1016/j.patcog.2010.09.020.
France, D. J., Shiavi, R. G., Silverman, S., Silverman, M., & Wilkes, M. (2000). Acoustical properties of speech as indicators of depression and suicidal risk. IEEE Transactions on Biomedical Engineering, 47(7), 829–837. https://doi.org/10.1109/10.846676.
Kyung Hak Hyun, Eun Ho Kim, & Yoon Keun Kwak. (n.d.). Improvement of emotion recognition by bayesian classifier using non-zero-pitch concept. ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005. https://doi.org/10.1109/roman.2005.1513797.
Milivojević, Z. N., Prlinčević, B. P., & Kostić, D. (2023). Procena emocionalnog stanja govornika statističkom analizom fundamentalne frekvencije. 2023 22st International Symposium INFOTEH-JAHORINA (INFOTEH).
Phonetic reduction and elaboration in emotional speech (emo DB). EmoDB - Database of Emotional Speech | Chair of Speech Communication. (n.d.). https://www.tu.berlin/en/kw/research/projects/emotional-speech.
Praat. Softonic. (n.d.). https://praat.en.softonic.com/ .
Sharma, S. (2021). Emotion recognition from speech using artificial neural networks and recurrent neural networks. 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence). https://doi.org/10.1109/confluence51648.2021.9377192.
Srinivas, V., Santhirani, Ch., & Madhu, T. (2014). Neural network based classification for speaker identification. International Journal of Signal Processing, Image Processing and Pattern Recognition, 7(1), 109–120. https://doi.org/10.14257/ijsip.2014.7.1.11.
T, T. (2022). Automatic speech recognition system using hybrid hidden Markov model and Human Emotion Recognition System. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4021329.
Tolkmitt, F. J., & Scherer, K. R. (1986). Effect of experimentally induced stress on vocal parameters. Journal of Experimental Psychology: Human Perception and Performance, 12(3), 302–313. https://doi.org/10.1037/0096-1523.12.3.302.
Wanare, A. P., & Dandare, S. N. (2014). Human Emotion Recognition From Speech. Journal of Engineering Research and Applications, 4(7), 74–78.
Wang, K.-C. (2015). Time-frequency feature representation using multi-resolution texture analysis and acoustic activity detector for real-life speech emotion recognition. Sensors, 15(1), 1458–1478. https://doi.org/10.3390/s150101458.
Womack, B. D., & Hansen, J. H. L. (1996). Classification of speech under stress using target driven features. Speech Communication, 20(1–2), 131–150. https://doi.org/10.1016/s0167-6393(96)00049-0.
Xu, S., Liu, Y., & Liu, X. (2013). Speaker recognition and speech emotion recognition based on GMM. Proceedings of the 3rd International Conference on Electric and Electronics. https://doi.org/10.2991/eeic-13.2013.102.
Zuber, S., & Vidhya, K. (2022). Detection and analysis of emotion recognition from speech signals using decision tree and comparing with support vector machine. 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES). https://doi.org/10.1109/icses55317.2022.9914046.
