The research area of Audio Intelligence Technology Research Laboratory embraces vast of Signal Processing targeted for audio signal processing, speech recognition, event detection, 3D audio and climate prediction. We are skillful to handle the subjects based on mathematical or statistical model for conventional approaches, analysis of multi-microphone array processing for acquiring effective 3D audio environments, and machine learning solutions employing trending methodologies
Research Field
• Speech Enhancement &Audio CodingNoise reduction for improvement of speech quality and recognition performanceDe-ReverberationAcoustic Echo Cancellation and Residual Echo SuppressionAudio and Speech Coding
• Speech and Sound Event RecognitionSpeech Recognition based on statistical and deep learning modelPronunciation and Language modelingAcoustic event and scene detection based on deep learning classification modelsSpeech synthesis from input texts by end-to-end synthesis system
• 3D AudioStereo audio channel to 5.1 channel UpmixingHead-related transfer function modeling for personalized audio experienceSound source separation in various objectsSound source localization
• Climate change predictionClimate factor prediction based on recurrent neural networks
Education
1994 KAIST (Ph.D-Electrical Engineering)
1990 Korea Advanced Institute of Science and Technology (M.S.-Electrical Engineering)
1988 Seoul National University (B.S.-Control and Instrumentation Engineering)
Professional Career
2017 - present GIST, Dean of Planning
2015 - 2017 GIST, Dean of Electrical Engineering and Computer Science
2008 - present GIST, Professor
2003 - 2008 GIST, Associate Professor
1998 - 2003 AT&T Labs-Research, Florham Park, New Jersey, Senior Technical Staff Member