Human Media Communication & Processing Laboratory (HuCom Lab)


Lab Name and Affiliation

Human Media Communication & Processing Laboratory (HuCom Lab)

Gwangju Institute of Science and Technology (GIST)

Lab Director (or Principal Investigator)

Hong Kook Kim

Prof. Hong Kook Kim received a B. S. degree in Control and Instrumentation Engineering from Seoul National University, Korea, in 1988. He then received both M.S. and Ph.D. degrees in Electrical Engineering from the Korea Advanced Institute of Science and Technology (KAIST), Korea in 1990 and 1994, respectively. He was a senior researcher at the Samsung Advanced Institute of Technology (SAIT), Korea, from 1990 to 1998. During 1998 to 2003, he was a senior technical staff member with the Voice Enabled Services Research Lab at AT&T Labs-Research, Florham Park, New Jersey. Since August 2003, he has been with the School of Information and Communications at Gwangju Institute of Science and Technology (GIST), Gwangju, Korea, as a Professor. He is currently an IEEE Senior Member and an affiliate member of IEEE Speech and Language Technical Committee. Since 2012, he has served as an editorial committee member and area editor of Digital Signal Processing. His current research interests include large vocabulary speech recognition, audio coding and speech/audio source separation, and embedded algorithms and solutions for speech and audio processing for handheld devices.

Lab Introduction

Human Media Communication & Processing Laboratory (HuCom Lab) has been founded at GIST in 2003. Under supervision of Prof. Hong Kook Kim, various topics in speech and audio signal processing and its applications have been researched.

We have been researching signal processing algorithms for multimedia, speech, audio, and communication fields, which are deeply related with method of human communication. Our major research of interests includes automatic speech recognition robust to background noise and speaker variability, realistic 3-dimensional audio coding and its processing. Moreover, unified technologies incorporating realistic audio, video, and dialog speech recognition for multimodal environment are also have been researching.

Specific topics we are interested in and researching currently are

* Speech & Audio-based Human Media Processing
* Human Media Communications
* Human Media Contents

Lab Contact E-mail