Emotion Recognition in Marathi Language by using Fast Fourier Transform
DOI:
https://doi.org/10.26438/ijcse/v7i10.4347Keywords:
Emotion Recognition, SER, AERAbstract
Emotion Recognition is a recent research area which can be applied in various applications. Speech Emotion is useful in E-learning, medical and in entertainment. The proposed work focuses on emotion recognition using Fast Fourier Transform and Marathi speech database. In this work six emotions are considered and Fast Fourier Transform is used for feature extraction and as a major feature for finding specific emotion. The Marathi words which represents the emotion like surprise and sad like Are Bapre (अरे बापरे ! ), Kiti Wilakshan (किती विलक्षण ! ), Are Deva (अरे देवा !) etc are used as a speech samples for analysis purpose. This paper highlights the overview of existing speech database as well as the newly developed Marathi emotional speech database. In this proposed work total 52 Marathi utterances are used in the experimental purpose. Fourier Transform is used to convert time domain signal into Frequency domain signal. The proposed experimental work gives 100% recognition rate for surprise and disgust emotion. Similarly 90% accuracy for sad emotion and 87.5% accuracy got for fear and angry emotion. The overall average recognition rate for six emotions is 93%. Very less accuracy rate i.e 62.5% got for happy emotion.
References
[1] Surabhi Vaishnav and Saurabh Mitra, “Speech Emotion Recognition: A Review”, International Journal of Engineering and Technology (IRJET), Vol. 03, Issue:04, Apr-2016.
[2] Leila Kerkeni, Youssef Serrestou, Mohamed Mbarki, Kosai Roof and Mohamed Ali Mahjoub, “Speech Emotion Recognition: Methods and Cases Study”, in Proceedings of the 10th International Conference on Agents and Artificial Intelligence (ICAART 2018) – Vol.2,Pages 175-182.
[3] Dhruvi Desai, “Emotion Recognition using Speech Signal: A Review”, International Research Journal of Engineering and Technology (IRJET), Vol. 05, Issue:04, Apr-2016.
[4] Shweta Sinha, “Analysis and Recognition of Dialects of Hindi Speech”, International Journal of Scientific Research in Computer Science and Engineering (IJSRCSE), Volume-3, Issue-5, Oct 2015.
[5] V.K. Jain and N. Tripathi, “Speech Features Analysis and Biometric Person Identification in Multilingual Environment”, International Journal of Scientific Research in Network Security and Cmmunications-6, Issue-1, February 2018.
[6] Agnihotri P.P., Shinde A.R. and Khanale P.B. “Development of Noise free Marathi Speech database using various Filtering Techniques”, Indian Journal of Research, Volume-5, Issue-2, February 2016.
[7] Oh-Wook Kwon, Kwokleung Chan, Jiucang Hao, Te-Won Lee, “Emotion Recognition by Speech Signals” EUROSPEECH 2003 - INTERSPEECH 2003 8th European Conference on Speech Communication and Technology Geneva, Switzerland, September 1-4, 2003.
[8] S.Lalitha, Sbhishek Madhavan, Bharath Bhushan, Srinivas Saketh,”Speech Emotion Recognition”, International Conference on Advances in Electronics, Computers and Communications(IJAECC), 2014.
[9] Nobuo Sato, Yasunari Obuchi, “Emotion Recognition using Mel-Frequency Cepstral Coefficients”, Journal of Natural Language Processing, pp 83-96, 2007.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
