The research area of the Speech and Audio Processing Laboratory encompasses vast area of speech and audio signal processing including single/multi-channel voice activity detection, speech enhancement, source localization, source separation, acoustic echo cancellation, speech/audio codecs, speech reinforcement, emotion recognition, and speaker recognition. Our approaches include signal processing approach based on signal characteristics and human perception model, machine learning approach based on ample database, and statistical signal processing approach utilizing both the signal model and the database information.
Research Field
• Single channel/Multichannel speech enhancement
• Source separation
• Voice activity detection
• Source localization
• Acoustic echo cancellation
• Speech/Audio codec and pre/post processing
• Speech reinforcement
• Emotion recognition
• Speaker recognition
Education
2008 Seoul National University (Ph. D. Electrical Engineering and Computer Science)
2002 Seoul National University (B. S. Electrical Engineering)
Professional Career
2012-Present Professor, School of Electrical Engineering and Computer Science, GIST
2008-2012 Senior Engineer, QCT Multimedia R&D and Standards, Qualcomm Inc.
Professional Services
• Associate Editor
-IEEE/ACM Transactions on Audio, Speech, and Language Processing