Speech Emotion Detection

Bharath P S; Dhruti S Gowda; Kunal R; Keerti Kulkarni

doi:10.32628/CSEIT2410317

Authors

Bharath P S Electronics and communication, B N M Institute of Technology, Bangalore, Karnataka, India Author
Dhruti S Gowda Electronics and communication, B N M Institute of Technology, Bangalore, Karnataka, India Author
Kunal R Electronics and communication, B N M Institute of Technology, Bangalore, Karnataka, India Author
Keerti Kulkarni Associate Prof, ECE, B N M Institute of Technology, Bangalore, Karnataka, India Author

DOI:

https://doi.org/10.32628/CSEIT2410317

Keywords:

Speech Emotion Recognition, Machine Learning Models, Neural Network Modelling

Abstract

The study is centered on the development of an advanced Speech Emotion Detection system utilizing Convolutional Neural Networks (CNN) and leveraging diverse datasets such as RAVDESS, CREMA-D, TESS, and SAVEE. Through rigorous analysis, the project achieved a notable accuracy rate of approximately 97% in identifying emotional cues within speech signals. The overarching goal of the research is to enrich emotional intelligence within technology, elevate interactions between humans and machines, and propel the domain of Speech Emotion Detection towards a more profound comprehension of human emotions conveyed through speech.

Downloads

Download data is not yet available.

References

Fatih Ozkaynak, Elif Bilge Tutkun, and Ceyhun Ozkan, "Feature engineering and selection for speech emotion recognition using machine learning techniques", Proceedings of the International Conference on Engineering, Science and Applications (ICESA), 2018 pp. 1-6.

Zhiyong Wu, Yuqing Wang, and Zhiqiu Zhou, "Exploring deep feature representations for speech emotion recognition", Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-8.

Chengzhi Cai, Yifan Hu, and Xiangyu Zeng, "Emotion recognition from speech using time-frequency analysis with convolutional neural networks", Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 683-687.

Tiancheng Guo, Wenqiang Xu, Jiankang Gao, and Zhen Cui, "Exploring feature fusion for speech emotion recognition with deep learning", Proceedings of the IEEE 17th International Symposium on Multimedia (ISM), April 2022, pp. 211-215.

Yifan Hu, Chengzhi Cai, and Xiangyu Zeng, "Feature learning for speech emotion recognition with deep autoencoders", Applied Sciences, 13(3), 2023, pp 1259. 6 Luis Fernando Garcia-Saura, Daniel Duque-Ruiz, Javier Alba-Castro, "A Deep Learning Approach for Speech Emotion Recognition Optimization Using Meta-Learning", Electronics, 12(11), 2023, pp. 1837.

Mohsen Mohammad, Md. Zahangir Al-Rashid, Md. Fayyaz Hossain, and Asif Ekram, "Deep convolutional neural networks for speech emotion recognition: A review", Sensors, 22(20), 2023, pp. 7615.

Yunzhe Liu, Hong Xu, Lingyun Zhang, and Yanhua Chen, "Speech emotion recognition with attention-based convolutional bi-LSTM networks", In Proceedings of the International Conference on Multimedia (MM '20), 2020, pp. 1652-1656.

Haoran Sun, Kevin Mao, and Yunhang Zhang, "Emotion recognition from speech using deep learning: A review", International Journal of Human-Computer Studies, 139, 2023, pp. 1-14.

Yang Xu, Weixing Chen, Furu Wang, and Yunhong Wang, "Towards more robust speech emotion recognition with transfer learning and data augmentation", In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2020, pp. 1557-1566.

Zhe Wang, Jintao Zhou, Junwen Chen, and Xinyu Chen, "Exploring the fusion of melfrequency cepstral coefficients and deep features for speech emotion recognition", In International Conference on Artificial Intelligence and Pattern Recognition, 2021, pp. 35-46.

Yunsheng Li, Zhiming Cui, Jiameng Fang, and Lei Wang, "Deep learning for multidimensional emotion recognition in speech", In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 678-682.