Chanwoo Kim

Chanwoo Kim has been a software engineer at Google, Inc. since 2013. He has been working for acoustic modeling for google speech recognition systems and enhancing noise robustness using deep learning techniques. He was a speech scientist at Microsoft from 2011 to 2013. Dr. Kim received a Ph.D. from the Language Technologies Institute of School of Computer Science Carnegie Mellon University in 2010. He received his B.S and M.S. degrees in Electrical Engineering from Seoul National University in 1998 and 2001, respectively. Dr. Kim’s doctoral research was focused on enhancing the robustness of automatic speech recognition systems in noisy environments. Between 2003 and 2005 Dr. Kim was a Senior Research Engineer at LG Electronics, where he worked primarily on embedded signal processing and protocol stacks for multimedia systems. Prior to his employment at LG, he worked for EdumediaTek and SK Teletech as a R&D engineer.

Google Publications

Previous Publications

  •   

    Power-normalized cepstral coefficients (pncc) for robust speech recognition

    Chanwoo Kim, Richard M. Stern

    IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (2012), 4101– 4104

  •   

    Two-microphone source separation algorithm based on statistical modeling of angle distributions

    Chanwoo Kim, Charbel Khawand, Richard M. Stern

    IEEE. Conf. Acoust, Speech, and Signal Processing (2012), pp. 4629–4632

  •   

    Binaural sound source separation motivated by auditory processing

    Chanwoo Kim, Kshitiz Kumar, Richard M. Stern

    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2011), pp. 5072-5075.

  •   

    Delta-spectral cepstral coefficients for robust speech recognition

    Kshitiz Kumar, Chanwoo Kim, Richard M. Stern

    IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (2011), 4784–4787

  •   

    Automatic selection of thresholds for signal separation algorithms based on interaural delay

    Chanwoo Kim, Richard M. Stern, Kiwan Eom, Jaewon Lee

    INTERSPEECH (2010), pp. 729-732

  •   

    Feature extraction for robust speech recognition based on maximizing the sharpness of the power distribution and on power flooring

    Chanwoo Kim, Richard M. Stern

    IEEE International Conference on Acoustics, Speech and Signal Processing (2010), pp. 4574-4577

  •   

    Nonlinear enhancement of onset for robust speech recognition

    Chanwoo Kim, Richard M. Stern

    INTERSPEECH (2010), pp. 2058-2061

  •   

    Signal Processing for Robust Speech Recognition Motivated by Auditory Processing

    Chanwoo Kim

    Ph.D. Thesis (2010)

  •   

    Feature Extraction for Robust Speech Recognition Using a Power-Law Nonlinearity and Power-Bias Subtraction

    Chanwoo Kim, Richard M. Stern

    INTERSPEECH (2009), pp. 28-31

  •   

    Power function-based power distribution normalization algorithm for robust speech recognition

    Chanwoo Kim, Richard M. Stern

    IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) (2009), pp. 188-193

  •   

    Robust speech recognition using a Small Power Boosting algorithm

    Chanwoo Kim, Kshitiz Kumar, Richard M. Stern

    IEEE Work Shop on Automatic Speech Recognition and Understanding (ASRU) (2009), pp. 243-248

  •   

    Signal Separation for Robust Speech Recognition Based on Phase Difference Information Obtained in the Frequency Domain

    Chanwoo Kim, Kshitiz Kumar, Bhiksha Raj, Richard M. Stern

    INTERSPEECH (2009), pp. 2495-2498

  •   

    Binaural and Multiple-Microphone Signal Processing Motivated by Auditory Perception

    Richard M. Stern, Evandro Gouvea, Chanwoo Kim, Kshitiz Kumar, Hyung-Min Park

    Hands-Free Speech Communication and Microphone Arrays (HSCMA) (2008), pp. 98-103

  •   

    Robust Signal-to-Noise Ratio Estimation Based on Waveform Amplitude Distribution Analysis

    Chanwoo Kim, Richard M. Stern

    INTERSPEECH (2008), pp. 2598-2601

  •   

    A Robust Formant Extraction Algorithm Combining Spectral Peak Picking and Root Polishing

    Chanwoo Kim, Kwang-deok Seo, Wonyong Sung

    EURASIP Journal on Applied Signal Processing, vol. 2006 (2006), pp. 1-16

  •   

    Efficient audio/video synchronization method for video telephony system in consumer cellular phones

    Chanwoo Kim, Kwang-deok Seo, Wonyong Sung, Soon-heung Jung

    IEEE Int. Conf on Consumer Electronics (2006), 137-138.

  •   

    Efficient media synchronization method for video telephony system

    Chanwoo Kim, Kwang-deok Seo, Wonyong Sung

    IEICE TRANSACTIONS on Information and Systems, vol. No. 6 (2006), pp.1901-1905

  •   

    Physiologically-motivated synchrony-based processing for robust automatic speech recognition

    Chanwoo Kim, Yu-Hsiang Chiu, Richard M. Stern

    INTERSPEECH (2006), pp. 1483-1486

  •   

    Robust DTW-based recognition algorithm for hand-held consumer devices

    Chanwoo Kim, Kwang-deok Seo

    IEEE Transactions on Consumer Electronics, vol. 51 (2005), pp. 699 - 709

  •   

    Robust dtw-based recognition algorithm for hand-held consumer devices

    Chanwoo Kim, Kwang-deok Seo

    IEEE Int. Conf. on Consumer Electronics (2005), pp. 433-434

  •   

    Implementation of an Intonational Quality Assessment System

    Chanwoo Kim, Wonyong Sung

    INTERSPEECH (2002), pp. 1225-1228

  •  

    Implementation of an Intonation and Pronunciation Checking System for Embedded System

    Chanwoo Kim

    (2001)

  •   

    Vowel pronunciation accuracy checking system based on phoneme segmentation and formants extraction

    Chanwoo Kim, Wonyong Sung

    Int. Conf Speech Processing (2001), pp.447-452