Welcome...

J. Kim MSc (Jaebok)

PhD Candidate

About Me

Jaebok kim is a PhD candidate at Human Media Interaction group in University of Twente. He studied speech emotion recognition during a master's program in Korea Advanced Institute of Science and Technology (2011, Daejon, Korea) and worked as a research engineer in LG Electronics Advanced Research Institute (2011-2014, Seoul, Korea). His current research focuses on affective and social signal processing using machine learning methods. In particular, he works on automatic emotion recognition from speech signals by using deep learning methods.

Expertise

Child
Robots
Speech Recognition
Speech
Learning
Ranking
Emotion
Moral Emotions
Secondary School
Interaction
Language
Audition
Refugee
Measurement Method
Conflict

Publications

Recent
Heron, L., Kim, J., Lee, M., El Haddad, K., Dupont, S., Dutoit, T., & Truong, K. P. (2018). A Dyadic Conversation Dataset on Moral Emotions. In 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) IEEE. DOI: 10.1109/FG.2018.00108
Lee, M., Kim, J., Truong, K., de Kort, Y., Beute, F., & IJsselsteijn, W. (2017). Exploring Moral Conflicts in Speech: Multidisciplinary Analysis of Affect and Stress. Paper presented at 7th International Conference on Affective Computing and Intelligent Interaction, San Antonio, United States.
Kim, J., Englebienne, G., Truong, K. P., & Evers, V. (2017). Towards Speech Emotion Recognition "in the wild" using Aggregated Corpora and Deep Multi-Task Learning. In Interspeech 2017: 20-24 August 2017, Stockholm (pp. 1113-1117). International Speech Communication Association (ISCA). DOI: 10.21437/Interspeech.2017
Kim, J., Englebienne, G., Truong, K. P., & Evers, V. (2017). Deep Temporal Models using Identity Skip-Connections for Speech Emotion Recognition. In MM '17: Proceedings of the 2017 ACM on Multimedia Conference (pp. 1006-1013). Association for Computing Machinery (ACM). DOI: 10.1145/3123266.3123353
Kim, J., Truong, K., Englebienne, G., & Evers, V. (2017). Learning spectral-temporal features with 3D CNNs for speech emotion recognition. Paper presented at 7th International Conference on Affective Computing and Intelligent Interaction, San Antonio, United States.
Gilmartin, E., Kim, J., Diallo, A., Zhao, Y., Chiarain, N. N., Su, K., ... Campbell, N. (2017). CARAMILLA - Speech Mediated Language Learning Modules for Refugee and High School Learners of English and Irish. In O. Engwall, J. Lopes, & I. Leite (Eds.), SLaTE 2017: proceedings of the Seventh ISCA Workshop on Speech and Language Technology in Education, SLaTE 2017 KTH Royal Institute of Technology.
Kim, J., & Park, J-S. (2016). Multistage Data Selection-based Unsupervised Speaker Adaptation for Personalized Speech Emotion Recognition. Engineering applications of artificial intelligence, 52, 126-134. DOI: 10.1016/j.engappai.2016.02.018
Kim, J., Truong, K. P., & Evers, V. (2016). Automatic detection of children's engagement using non-verbal features and ordinal learning. In Proceedings of the Workshop on Child Computer Interaction (WOCCI 2016) (pp. 29-34). Baixas, France: ISCA. DOI: 10.21437/WOCCI.2016-5
Kim, J., Truong, K. P., Charisi, V., Zaga, C., Evers, V., & Chetouani, M. (2016). Multimodal Detection of Engagement in Groups of Children Using Rank Learning. In Proceedings of the 7th International Workshop on Human Behavior Understanding, HBU 2016 (pp. 35-48). (Lecture Notes in Computer Science; Vol. 9997). London: Springer Verlag. DOI: 10.1007/978-3-319-46843-3_3

UT Research Information System

Google Scholar Link

Education

I've supervised groups of MS and BS students in HMI, Computer Science, and other groups or departments for their research projects and thesis.

 

Also, I've been involved in courses of artificial intelligence and machine learning topics.

Projects

I've worked on two EU 7'th program funded projects: SQUIRREL and TERESA.

In SQUIRREL, I mainly investigated automatic engagement recognition methods for a group of children who interact with a social robot. In particular, I am interested in ordinal coding and learning methods that model children's orders in a group.

In TERESA, I developed automatic emotion recognition methods using speech signals and deep learning methods. I researched large-aggregated corpora and deep temporal architectures for speech emotion recognition.

Finished Projects

Contact Details

Visiting Address

University of Twente
Faculty of Electrical Engineering, Mathematics & Computer Science
Zilverling (building no. 11)
Hallenweg 19
7522NH  Enschede
The Netherlands

Navigate to location

Mailing Address

University of Twente
Faculty of Electrical Engineering, Mathematics & Computer Science
Zilverling
P.O. Box 217
7500 AE Enschede
The Netherlands

Additional Contact Information

You can access all developed softwares related to my research:

https://github.com/batikim09/

Social Media