Woohyung Lim (임우형), Ph.D
Applied AI Research Group Leader / Vice President
Address: ISC, 30, Magokjungang 10-ro, Gangseo-gu, Seoul, 07796, Korea
Email: w.lim (at) lgresearch (dot) ai
Research Interests
Data Intelligence (Intelligent Decision Making using AI)
Artificial intelligence that helps make optimal decisions based on prediction, optimization, and reasoning techniques
Prediction
Prediction, Regression, Time-series Forecasting, Generative Models
Optimization
Deep Reinforcement Learning
Reasoning
Explainable AI, Causal Learning, Disentangled Representation Learning
Transfer Learning - Using knowledge with a lot of labelled data to a task with little labelled data
Applications
Anomaly Detection, Demand/Sales/Raw Materials Price Forecasting, Process Optimization, Molecular Design, Reaction Prediction
Materials Intelligence (Materials Discovery and Design using AI)
Artificial intelligence that helps make new materials based on prediction, and optimization techniques
Applications
Universal Molecular Design, Neural Chemical Synthesis
Experience
LG AI Research (2022.12 ~ Present)
Research Group Leader / Vice President, Applied AI Research Group
Time-Series Forecasting, Prediction, Anomaly Detection, Reinforcement Learning, Recommendation, Generative Models, Representation Learning
Materials Intelligence, Materials Discovery, AI based Molecular Design, AI based Reaction Prediction
AI Service Platform
LG AI Research (2020.12 ~ 2022.11)
Lab Leader / Vice President, Applied AI Research Lab
Time-Series Forecasting, Prediction, Anomaly Detection, Reinforcement Learning, Recommendation, Generative Models, Representation Learning
LG Sciencepark (2020.09 ~ 2020.11)
Lab Leader / Research Fellow, Data Intelligence Lab, AI Division
Research Fellow
Time-Series Forecasting, Prediction, Anomaly Detection, Reinforcement Learning, Generative Models, Representation Learning
LG Sciencepark (2019.03 ~ 2020.08)
Research Fellow, AI Division
Data Intelligence Task Leader
Time-Series Forecasting, Prediction, Anomaly Detection, Reinforcement Learning, Generative Models, Representation Learning
SK Telecom (2013.05 ~ 2019.02)
Principal Research Engineer, AI Tech. Unit
Lead Acoustic Models and Front-end Processing Researcher
Lead Speech Recognition Client/Server Software Architect
NUGU Platform, Speech Recognition, Multi-Channel Speech Enhancement, Speech Recognition Client/Server
Samsung Electronics (2007.09 ~ 2013.04)
Senior Software Engineer, Mobile Division
S Voice (Speech Recognition and Natural Language Processing), S Translator (Machine Translation)
Mobile Phone Multimedia Software Development (Video/Music Player, Video Telephony)
Education
Doctor of Philosophy, Machine Learning / Speech Recognition, Seoul National University (2007.08)
Dissertation: "Statistical Approaches to Robust Speech Recognition in Adverse Environments"
Projects: Robust Speech Recognition, Speech Enhancement, Speaker Adaptation, Audio Codec, Speech Synthesis, Disease of Vocal Cord and Larynx Detection, Cochlear Implant
Master's degree, Machine Learning / Speech Recognition, Seoul National University (2002.02)
Thesis: "Score Normalization for Text-Independent Speaker Verification Systems"
Projects: Robust Speech Recognition, Speech Synthesis, Cochlear Implant
Bachelor's degree, Electrical and Computer Engineering, Seoul National University (2000.02)
Selected Projects
LG AI Research
Naphtha Scheduling Optimization, 2022 ~
AI Based PCB Layout Design, 2021 ~
Recommendation, 2021 ~
Music Composer, 2021 ~
Demand/Sales Forecasting, 2021 ~
Battery Anomaly Detection, 2020 ~
AI Materials Discovery, 2020 ~
Battery Discharge Capacity Prediction, 2020 ~ 2022
Network Quality Anomaly Detection, 2020 ~ 2021
Battery Cycle-life Prediction, 2020 ~ 2021
AI Drug Discovery, 2020 ~ 2021
SK Telecom
NUGU Speech Recognition , 2015 ~ 2019
T-map Speech Recognition, 2014 ~ 2019
SK Broadband Settop Box Speech Recognition, 2014 ~ 2019
FPGA Accelerator for Speech Recognition, 2017 ~ 2019
Contact Center Speech-to-Text Solution, 2014 ~ 2019
Voice Phishing Detection, 2018 ~ 2019
Samsung Electronics
S Translator (Galaxy S4 ~), 2012 ~ 2013
S Voice (Galaxy S3 ~), 2012 ~ 2013
Multimedia Framework, 2007 ~ 2012
Selected Publications
H. Ihm, S. Han, W. Lim, "Composer AI with tap-to-pitch generator," Neurips Workshop on Machine Learning for Creativity and Design, Dec. 2021.
S. Han, H. Ihm, W. Lim, "Symbolic Music Loop Generation with VQ-VAE," arXiv:2111.07657, Nov. 2021.
S. S. Han, I. J. Moon, S. H. Kim, J.-I. Na, M. S. Kim, G. H. Park, I. Park, K. Kim, W. Lim, J. H. Lee, S. E. Chang, "Assessment of deep neural networks for the diagnosis of benign and malignant skin neoplasms in comparison with dermatologists: A retrospective validation study," PLoS medicine, Nov. 2020.
S. S. Han, I. Park, S. E. Chang, W. Lim, M. S. Kim, G. H. Park, J. B. Chae, C. H. Huh, J.-I. Na, "Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders," Journal of Investigative Dermatology, Mar. 2020.
S. S. Han, I. J. Moon, W. Lim, I. S. Suh, S. Y. Lee, J.-I. Na, S. H. Kim, S. E. Chang, "Keratinocytic Skin Cancer Detection on the Face Using Region-based Convolutional Neural Network," JAMA Dermatology, Jan. 2020.
M. Ahn, S. J. Hwang, W. Kim, S. Jung, Y. Lee, M. Chung, W. Lim, Y. Kim, "AIX: A High Performance and Energy Efficient Inference Accelerator on FPGA for a DNN-based Commercial Speech Recognition," Design, Automation & Test in Europe Conference & Exhibition, Mar. 2019.
S. S. Han, W. Lim, M. S. Kim, I. Park, G. H. Park, S. E. Chang, "Interpretation of the Outputs of a Deep Learning Model Trained with a Skin Cancer Dataset," Journal of Investigative Dermatology, Oct. 2018.
S. S. Han, M. S. Kim, W. Lim, G. H. Park, I. Park, S. E. Chang, "Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm," Journal of Investigative Dermatology, Feb. 2018.
S. S. Han, G. H. Park, W. Lim, M. S. Kim, J.-I. Na, I. Park, S. E. Chang, "Deep Neural Networks Show an Equivalent and Often Superior Performance to Dermatologists in Onychomycosis Diagnosis: Automatic Construction of Onychomycosis Datasets by Region-based Convolutional Deep Neural Network," PLOS ONE, Jan. 2018.
W. Lim, C. W. Han, N. S. Kim, "Computationally Efficient Cepstral Domain Feature Compensation," IEICE TRANS. INF. & SYST., Jan. 2009.
W. Lim, C. W. Han, J. W. Shin, N. S. Kim, "Cepstral Domain Feature Compensation based on Diagonal Approximation," ICASSP, Mar. 2008.
K.-H. Lee, W. Lim, N.-S. Kim, J.-H. Chang, "GMM-Based Gender Identification Employing Group Delay," The Journal of the Acoustical Society of Korea, Aug. 2007.
J. W. Shin, W. Lim, J. Sung, N. S. Kim, "Speech Reinforcement based on Partial Specific Loudness," INTERSPEECH, Aug. 2007.
W. Lim, N. S. Kim, "Feature Compensation Incorporating Modeling Error Statistics," IEEE Signal Processing Letters, Jun. 2007.
W. Lim, J. K. Kim, N. S. Kim, "Feature Compensation using More Accurate Statistics of Modeling Error," ICASSP, Apr. 2007.
J.-H. Chang, W. Lim, N. S. Kim, "Signal Modification Incorporating Perceptual Weighting Filter," INTERSPEECH, Sep. 2006.
Y. J. Kim, W. Lim, N. S. Kim, "Clean Speech Feature Estimation based on Soft Spectral Masking," INTERSPEECH, Sep. 2006.
W. Lim, B. K. Kim, N. S. Kim, "Feature Compensation based on Switching Linear Dynamic Model and Soft Decision," INTERSPEECH, Sep. 2005.
N. S. Kim, D. J. Seo, W. Lim, "An Approach to Robust Unsupervised Speaker Adaptation," IEEE Signal Processing Letters, May 2005.
N. S. Kim, W. Lim, R. M. Stern, "Feature Compensation based on Switching Linear Dynamic Model," IEEE Signal Processing Letters, May 2005.
Y. J. Kim, H. W. Kim, W. Lim, N. S. Kim, "Feature Compensation Technique for Robust Speech Recognition in Noisy Environments," INTERSPEECH, Sep. 2003.
D. K. Kim, Y. J. Kim, W. Lim, N. S. Kim, "Online Adaptation using Speatransformation Space Model Evolution," ICASSP, Apr. 2003.
W. Lim, N. S. Kim, "Bayesian Approach to Text Independent Speaker Verification," ICSP, Aug. 2001.
Selected Patents
"Apparatus for Cancellation of Acoustic Echo and Computer Program Therefore," Korea Patent, 2017.
"Method and System for Supporting a Translation-based Communication Service and Terminal Supporting the Service," US Patent, 2016.
"Method for Extracting Feature Parameter of Speech Recognition and Apparatus using the Same," Korea Patent, 2013.
"Supporting Method And System For Communication Service, and Electronic Device Supporting the Same," Korea Patent, 2013.