ABSTRACT
In real-life scenarios, artificial customer service is capable of accurately recognizing customer feedback emotions. However, it faces limitations in terms of working hours and high costs. While intelligent customer service can handle most tasks, it lacks the ability to perceive real-time changes in user emotions through tone, thus affecting the overall user experience. Considering these social pain points, this paper proposes the use of Support Vector Machine (SVM) algorithm for Speech Emotion Recognition. By extracting ten distinct speech features and applying classification techniques, the results indicate that the model achieves an accuracy rate of 90%. The system consists of both hardware and software components. When the system detects user input data, it autonomously analyzes the emotions and generates a radar chart as the result. Human and machine customer service representatives utilize the emotion recognition results to develop a tailored solution for the user. A mobile application displays the detection results and provides specific solutions based on different emotions. In addition to its application in intelligent customer service and other smart interactive domains, this system can also be applied in various fields such as healthcare and transportation safety.
- Li, Y., Tao, J., Schuller, B., Shan, S., Jiang, D., & Jia, J. 2018, May. Mec 2017: Multimodal emotion recognition challenge. In 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia) (pp. 1-5). IEEE.Google Scholar
- Stappen, L., Baird, A., Christ, L., Schumann, L., Sertolli, B., Messner, E. M., ... & Schuller, B. W. 2021. The MuSe 2021 multimodal sentiment analysis challenge: sentiment, emotion, physiological-emotion, and stress. In Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge (pp. 5-14)Google Scholar
- Koolagudi, S. G., & Rao, K. S. 2012. Emotion recognition from speech: a review. International journal of speech technology, 15, 99-117.Google Scholar
- Dileep, A. D., & Sekhar, C. C. 2013. GMM-based intermediate matching kernel for classification of varying lengt patterns of long duration speech using support vector machines. IEEE Transactions on Neural Networks and Learning Systems, 25(8), 1421-1432.Google Scholar
- Deng, L., & Yu, D. 2014. Deep learning: methods and applications. Foundations and trends® in signal processing, 7(3–4), 197-387.Google Scholar
- Wöllmer, M., Metallinou, A., Eyben, F., Schuller, B., & Narayanan, S. 2010. Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional lstm modeling.Google Scholar
- Niu, Y., Zou, D., Niu, Y., He, Z., & Tan, H. 2017. A breakthrough in speech emotion recognition using deep retinal convolution neural networks. arXiv preprint arXiv:1707.09917.Google Scholar
- Ramakrishnan, S., & El Emary, I. M. 2013. Speech emotion recognition approaches in human computer interaction. Telecommunication Systems, 52, 1467-1478.Google Scholar
- B. Yang and M. Lugger, “Emotion recognition from speech signals using new harmony features,” Signal Process., vol. 90, pp. 1415–1423, 2010.Google ScholarDigital Library
- Zepf, S., Hernandez, J., Schmitt, A., Minker, W., & Picard, R. W. 2020. Driver emotion recognition for intelligent vehicles: A survey. ACM Computing Surveys (CSUR), 53(3), 1-30.Google Scholar
- Albudoor, N., & Peña, E. D. 2022. Identifying language disorder in bilingual children using automatic speech recognition. Journal of Speech, Language, and Hearing Research, 65(7), 2648-2661.Google Scholar
Index Terms
- Intelligent Customer Service System Based on Speech Emotion Recognition
Recommendations
Emotion recognition from speech: a review
Emotion recognition from speech has emerged as an important research area in the recent past. In this regard, review of existing work on emotional speech processing is useful for carrying out further research. In this paper, the recent literature on ...
Application of Emotion Recognition and Modification for Emotional Telugu Speech Recognition
AbstractMajority of the automatic speech recognition systems (ASR) are trained with neutral speech and the performance of these systems are affected due to the presence of emotional content in the speech. The recognition of these emotions in human speech ...
Comments