Sakorn MekruksavanichAnuchit JitpattanakulNarit HnoohomUniversity of PhayaoKing Mongkut's University of Technology North BangkokMahidol University2020-08-252020-08-252020-03-012020 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2020. (2020), 71-742-s2.0-85085622170https://repository.li.mahidol.ac.th/handle/123456789/57655© 2020 IEEE. Over the last decade, speech emotion recognition (SER) has become an interesting and challenging topic in the human behavior analysis research field. The objective of this area of research is to classify the emotional states of people based on the speech patterns of humans. Currently, the focus of this research field is on the identification of the effectiveness of automatic classifiers that can enhance the efficiency of the classification in practical applications, particularly those used in telecommunication services. Negative emotions, such as sadness, anger, disgust, and fear, can provide a significant amount of beneficial data to both the user of the quality assurance platform and the customer. This paper examines the complicated task involving recognition of negative emotions in human speech data by employing a deep learning technique. Four open emotional speech datasets are used in this research in order to identify a deep learning classifier that provides good efficiency for use with negative emotion speech data. Furthermore, the classifier with the best performance was also tested with a Thai language dataset. Based on the experimental results, the one-dimensional convolution neural network was determined to be the classifier that has the most outstanding performance level for tasks involving negative emotion recognition in the Thai language with a level of accuracy at 96.60%.Mahidol UniversityArts and HumanitiesComputer ScienceEnergyEngineeringMedicineSocial SciencesConference PaperSCOPUS10.1109/ECTIDAMTNCON48261.2020.9090768