Abstract
In this work, the authors attempt to an improved speech emotion recognition (SER) using ant colony optimization (ACO) algorithm. Observation shows mostly discussed spectral features consider the entire frequency range hence containing irrelevant information. The desired modeling requires a larger memory, reduces the system response, and decreases the accuracy. Thus, the authors focus only on the spectral roll-off (SR), spectral centroid (SC), and spectral flux (SF), log energy, and formants at a few chosen sub-bands for the intended analysis. The emotional voice samples have been collected from the surrey audio-visual expressive emotion (SAVEE) dataset which is easily accessible and is in the English language. The ACO algorithm is further explored to develop a more discriminative and relevant feature set of the baseline techniques. Finally, the individual optimized feature sets are concatenated to develop suitable identification system models. The K-nearest neighbor (KNN) classifier has been chosen for the proposed investigation due to its simplicity and suitability in the reduced feature domain. Results show the hybridized optimized feature set using the ACO technique has indeed improved the SER accuracy as compared to the baseline feature sets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haridas VA, Marimuthu R, Sivakumar VG (2018) A critical review and analysis of techniques of speech recognition: the road ahead. Int J Knowl-Based Intell Eng Syst 22(1):39–57
Gomathy M (2021) Optimal feature selection for speech emotion recognition using enhanced cat swarm optimization algorithm. Int J Speech Technol 24(1):155–163
Özseven T (2019) A novel feature selection method for speech emotion recognition. Appl Acoust 146:320–326
Agarwal G, Om H (2020) Performance of deer hunting optimization based deep learning algorithm for speech emotion recognition. Multimedia Tools Appl 1–32
Palo HK, Kumar P, Mohanty MN (2017) Emotional speech recognition using optimized features. IJRECE 5(4):4–9
Bandela SR, Kumar TK (2019) Speech emotion recognition using semi-NMF feature optimization. Turk J Electr Eng Comput Sci 27(5):3741–3757
Langari S, Marvi H, Zahedi M (2020) Improving of feature selection in speech emotion recognition based-on hybrid evolutionary algorithms. Int J Nonlinear Anal Appl 11(1):81–92
Singh A (2020) Speech emotion recognition using enhanced cat swarm optimization algorithm. Int J Inf Technol (IJIT), 6(5) (2020).
Shahzadi A, Ahmadyfard A, Harimi A, Yaghmaie K (2015) Speech emotion recognition using nonlinear dynamics features. Turkish J Electr Eng Comp Sci 23
Palo HK, Sahoo S, Subudhi AK (2021) Dimensionality reduction techniques: principles, benefits, and limitations. data analytics in bioinformatics: a machine learning perspective. Wiley, pp 77–107
Daneshfar F, Kabudian SJ (2020) Speech emotion recognition using discriminative dimension reduction by employing a modified quantum-behaved particle swarm optimization algorithm. Multimedia Tools Appl 79(1):1261–1289
Palo HK (2020) The effect of age, gender, and arousal level on categorizing human affective states. In: Emotion and information processing, Springer, Cham, pp 97–124
Hong-zhang Y (2013) Feature selection of speech emotional recognition based on ant colony optimization algorithm. Comput Simul 4 (2013)
Nayak J, Vakula K, Dinesh P, Naik B, Mishra M (2020) Ant colony optimization in data mining: critical perspective from 2015 to 2020. In: Innovation in electrical power engineering, communication, and computing technology, pp 361–374
Paliwal KK (1998) Spectral sub-band centroid features for speech recognition. In: Acoustics, speech and signal processing (ICASSP), vol 2, pp 617–620
Palo HK, Behera D, Rout BC () Comparison of classifiers for speech emotion recognition (SER) with discriminative spectral features. In Advances in intelligent computing and communication, Springer, Singapore pp 78–85
Dorigo M, Socha K (2006) An introduction to ant colony optimization. In: Handbook of metaheuristic, vol 26, issue 1. IRIDIA, Brussels. ISSN 1781-3794
Pasteels JM, Deneubourg J-L, Goss S (1987) Self-organization mechanisms in ant societies (i): Trail recruitment to newly discovered food sources. Experientia Suppl 54:155
Palo HK, Mohanty MN (2020) Analysis of speech emotions using dynamics of prosodic parameters. In: Cognitive informatics and soft computing. Springer, Singapore, pp 333–340
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
Panigrahi, S.N., Palo, H.K. (2022). Analysis and Recognition of Emotions from Voice Samples Using Ant Colony Optimization Algorithm. In: Mishra, M., Sharma, R., Kumar Rathore, A., Nayak, J., Naik, B. (eds) Innovation in Electrical Power Engineering, Communication, and Computing Technology. Lecture Notes in Electrical Engineering, vol 814. Springer, Singapore. https://doi.org/10.1007/978-981-16-7076-3_20
Download citation
DOI: https://doi.org/10.1007/978-981-16-7076-3_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7075-6
Online ISBN: 978-981-16-7076-3
eBook Packages: EnergyEnergy (R0)