Abstract
Emotion recognition is the most relevant field in human–machine interaction. In this paper, primary emotions are recognized as these form the base for secondary emotions. This paper performs emotion recognition by experimenting on the existing classifier K-nearest neighbor (KNN) by adding a quantization layer in its architecture to decrease its processing time. This reduction is done by making quality selection from extracted features by the method of quantization, also maintaining its simplicity and performance accuracy. MFCCs were selected from the set of acoustic features as they are robust to mimicry and noise. The Berlin, Hindi and French experimental datasets were used for comparing the classifiers’ accuracy and processing time. Q-KNN proved to be the fastest with the accuracy of 80% as compared to KNN with 80% and VQ with 70%, thus satisfying the purpose of the experiment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M.K. Gill, R. Kaur, J. Kaur, Vector quantization based speaker identification, Int. J. Comput. Appl. (0975−8887) 4(2), (2010)
H. Behravan, Dialect and Accent Recognition, University of Eastern Finland, December 2012
L.E. Boucheron, P.L. De Leon, On the Inversion of mel-frequency cepstral coefficients for speech enhancement applications, Klipsch school of electrical and computer engineering new Mexico State University (2008)
D. Mahmoodi, H. Marvi, M. Taghizadeh, A. Soleimani, F. Razzazi, M. Mahmoodi, Age estimation based On speech features and support vector machine, in 3rd Computer Science and Electronic Engineering Conference (2011)
J.I. Godino-Llorente*, P. Gómez-Vilda, Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors, IEEE. Trans. Biomed. Eng. 51(2), (2004)
D. Gupta, R. Mounima; C. Navya Manjunath, P.B. Manoj, Isolated word speech recognition using vector quantization, Int. J. Adv. Res. Comput. Sci. Software. Eng. (2012)
T.-L. Pao, Y.-T. Chen, J.-H. Yeh, Y.-M. Cheng, Y.-Y. Lin, A comparative study of different weighting schemes on KNN-based emotion recognition in mandarin speech, (Tatung University 40 ChungShan North Road, 3rd Section Taipei 104, Taiwan, 2007)
I.T. Meftah, N.L. Thanh, C.B. Amar, Emotion recognition using KNN classification for user modeling and sharing of affect states, (University of Nice, University of Sfax, Tunisia, 2012)
Applicational Areas of MFCC in CiiT, Int. J. Artif. Intell. Syst. Mach. learn. May (2017 issue)
M.C. Sezgin, B. Gunsel, G.K. Kurt, Perceptual audio features for emotion detection, Sezgin et al., EURASIP J. Audio. Speech. Music. Process. 16, (2012)
P. Kapoor, N. Thakur, Applicational areas of MFCC, Artif. Intell. Syst. Mach. Learn. 9(5), 82–86 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kapoor, P., Thakur, N. (2021). Emotion Recognition Using Q-KNN: A Faster KNN Approach. In: Gupta, D., Khanna, A., Bhattacharyya, S., Hassanien, A.E., Anand, S., Jaiswal, A. (eds) International Conference on Innovative Computing and Communications. Advances in Intelligent Systems and Computing, vol 1165. Springer, Singapore. https://doi.org/10.1007/978-981-15-5113-0_62
Download citation
DOI: https://doi.org/10.1007/978-981-15-5113-0_62
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5112-3
Online ISBN: 978-981-15-5113-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)