Abstract
Speech Emotion Recognition (SER) using speech signals to detect our emotions is gaining popularity in the field of Human–Computer Interactions. The emotional state of a speaker is identified from a speech by using Mel Frequency Cepstral Coefficients (MFCC) feature and Gammatone Cepstral Coefficients (GTCC) as features with less dimensionality, and classification is done based on vector quantization (VQ) modelling and minimum distance classifier. The source used was the Berlin database which has the recorded utterances in various emotions like anger, boredom, sad and neutral spoken by actors. The speech signals are first digitized and pre-emphasized, after which it gets converted into frames. The frames are then multiplied with hamming window to reduce damping at higher frequencies. Then from the windowed speech signal, Mel Frequency Cepstral Coefficients (MFCC) feature and Gammatone Cepstral Coefficients (GTCC) are extracted. The extracted features are applied to the VQ models and based on minimum distance; the emotion is classified. The Unsupervised machine learning algorithm K-MEANS is used as a classifier and then the comparison is carried out between the accuracy of MFCC and GTCC features in distinguishing the emotions such as anger, sadness, boredom, and neutral.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Revathi, A., Jeyalakshmi, C.: Emotion recognition: different sets of features and models. Int. J. Speech Technol. 22(3), 473–482 (2019). http://www.scopus.com/inward/record.url?eid=2-s2.0-85049946565&partnerID=MN8TOARS
Revathi, A., Jeyalakshmi, C.: Comparative analysis on the use of features and models for validating language identification system. In: Proceedings of the International Conference on Inventive Computing and Informatics, ICICI 2017, pp. 693–698 (2018). http://www.scopus.com/inward/record.url?eid=2-s2.0-85048347705&partnerID=MN8TOARS
Dharani, D., Revathi, A.: Singer identification using clustering algorithm. In: International Conference on Communication and Signal Processing, ICCSP 2014—Proceedings, pp. 1927–1931 (2014). http://www.scopus.com/inward/record.url?eid=2-s2.0-84916216617&partnerID=MN8TOARS
Revathi, A., Jeyalakshmi, C.: Efficient speech recognition system for hearing impaired children in classical tamil language. Int. J. Biomed. Eng. Technol. 26 (2018). http://www.inderscience.com/offer.php?id=89261
Daniel, D., Revathi, A.: Raga identification of carnatic music using iterative clustering approach. In: Proceedings of the International Conference on Computing and Communications Technologies, ICCCT 2015, pp. 19–24 (2015). http://www.scopus.com/inward/record.url?eid=2-s2.0-84961827474&partnerID=MN8TOARS
Revathi, A., Sasikaladevi, N., Nagakrishnan, N., Jeyalakshmi, C.: Robust emotion recognition from speech: Gammatone features and models. In: Proceedings of the 2nd International Conference on Communication and Electronics Systems, ICCES 2017 (2018). https://link.springer.com/article/10.1007/s10772-018-9546-1
Bombatkar, A., Bhoyar, G., Morjani, K., Gautam, S., Gupta, V.: Emotion recognition using speech processing using K-nearest neighbor algorithm. Int. J. Eng. Res. Appl. (2004). http://ijera.com/special_issue/ICIAC_April_2014/EN/V4/EN-2026871.pdf
Revathi, A., Jeyalakshmi, C., Muruganantham, T.: Perceptual features based rapid and robust language identification system for various Indian classical languages. Lect. Notes Comput. Vis. Biomech. (2018). https://link.springer.com/chapter/10.1007%2F978-3-319-71767-8_25
Revathi, A., Krishnamurthi, V., Jeyalakshmi, C.: Alphabet model-based short vocabulary speech recognition for the assessment of profoundly deaf and hard of hearing speeches. Int. J. Modell. Identif. Control 23 (2015). http://www.inderscience.com/offer.php?id=69932
Rahana, F., Raseena, P.E.: Gammatone cepstral coefficients for speaker identification. Int. J. Adv. Res. Electr. Electron. Instrum. Eng. 2 (2013). https://www.ijareeie.com/upload/2013/dec13-special/63_rahana_fathima.pdf
Wang, H., Zhang, C.: The application of gammatone frequency cepstral coefficients for forensic voice comparison under noisy conditions. Austr. J. Foren. Sci. (2019). https://www.tandfonline.com/doi/full/10.1080/00450618.2019.1584830
Martinez, J., Perez, H., Escamilla, E., Suzuki, M.M.: Speaker recognition using mel frequency cepstral coefficients (MFCC) and vector quantization (VQ) techniques. In: CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers, pp. 248–251, Cholula, Puebla, Mexico (2012)
Valero, X., Alias.: Gammatone cepstral coefficients: biologically inspired features for non-speech audio classification. IEEE Trans. Multimed. 14(6), 1684–1689 (2012). https://ieeexplore.ieee.org/document/6202347
Adiga, A., Magimai, M., Seelamantula, C.S.: Gammatone wavelet cepstral coefficients for robust speech recognition. https://core.ac.uk/download/pdf/192527929.pdf
Gabrielle, K.L.: Evaluating gammatone frequency cepstral coefficients with neural networks for emotion recognition from speech. Cornell University (2018). https://arxiv.org/abs/1806.09010
Ayoub, B., Jamal, K., Arsalane, Z.: Gammatone frequency cepstral coefficients for the speaker identification over VoIP networks. In: 2016 International Conference on Information Technology for Organizations Development (IT4OD), Fez, Morocco, pp. 1–5 (2016). https://ieeexplore.ieee.org/document/7479293
Declaration
We have taken permission from competent authorities to use the images/data as given in the paper. In case of any dispute in the future, we shall be wholly responsible.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Revathi, A., Neharika, B., G, G. (2022). Emotion Recognition from Speech Using Multiple Features and Clusters. In: Bhateja, V., Tang, J., Satapathy, S.C., Peer, P., Das, R. (eds) Evolution in Computational Intelligence. Smart Innovation, Systems and Technologies, vol 267. Springer, Singapore. https://doi.org/10.1007/978-981-16-6616-2_25
Download citation
DOI: https://doi.org/10.1007/978-981-16-6616-2_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6615-5
Online ISBN: 978-981-16-6616-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)