Alumni

Send feedbacks & updates to root at ai.korea.ac.kr

Ph. D

이태우(Taewoo Lee)

Ph.D (2016) Parallel SRP-PHAT for GPUs
Ms (2012) Graphics processing unit based real-time implementation of steered response power-phase transform for human-robot interaction
Contact roboticist at ai.korea.ac.kr
Current Samsung Electronics


임현택(Hyeontaek Lim)

Ph.D (2016) Speaker selective source localization for non-trivial noise environments
Ms (2010) Continuous speech visualization using phoneme recognition
Contact htlim at ai.korea.ac.kr
Current Samsung Electronics


유인철 (Inchul Yoo)

Ph.D (2015) Robust voice activity detection using formant frequencies
Ms (2008) New similarity measure using spectral peaks for robust distant sound recognition
Contact icyoo at ai.korea.ac.kr
Current Korea University


이협우(Hyubwoo Lee)

Ph.D (2015) Multi-channel voice activity detection using multi-source
Ms (2009) Space-time voice activity detection for mobile environments
Contact purple1002 at naver.com
Current KT Corporation


조영규(Youngkyu Cho)

Ph.D (2011) Robust speaker localization using steered response voice power
Ms (2003) Support vector machine을 이용한 음소 인식
Contact ycho7512 at gmail.com
Current LG Electronics


김동현(Donghyun Kim)

Ph.D (2008) Acoustic model adaptation using linear spectral transformation for robust speech recognition
Ms (2004) Fast speech adaptation using linear spectral transtorm for additive and convolutional noises
Contact dawnkann at etri.kr
Current ETRI


Master

오현우 (Hyunwoo Oh)

Ms (2020) 지연 보상을 적용한 파이프라인 방식 확률적 경사 하강법
Contact komjii at ai.korea.ac.kr
Current Saltlux (전문연구요원)

이건녕 (Keonnyeong Lee)

Ms (2020) 다수 화자 음성 변환을 위한 VAE의 잠재 공간 Disentanglement와 변환 경로 학습
Contact gnl0813 at ai.korea.ac.kr
Current Koh Young Technology (전문연구요원)

임성균 (Seonggyun Leem)

Ms (2020) 심층신경망 기반 음성 인터페이스의 환경 적응을 위한 선형 스펙트럼 특징 변환
Contact sgleem at ai.korea.ac.kr
Current UT Dallas (유학)

고봉구 (Bonggu Ko)

Ms (2020) Cycle-consistency를 이용한 다수 화자 한국어 음성변환
Contact keacotle at ai.korea.ac.kr
Current Withcat

정동화 (Donghwa Jeong)

Ms (2020) Triple attention을 이용한 음성 인식
Contact donghwa at ai.korea.ac.kr
Current TmaxSoft (전문연구요원)

이효원 (Hyowon Lee)

Ms (2019) Pipelined stochastic gradient descent for training deep neural network models
Contact hwl at ai.korea.ac.kr
Current KT Corporation

임단 (Dan Im)

Ms (2018) Improving seq2seq by revising attention mechanism for speech recognition
Contact imdanboy at ai.korea.ac.kr
Current Kakao (전문연구요원)

이은상 (Eunsang Lee)

Ms (2017) Parallel training for deep neural network based speech recognizers
Contact alexlee at ai.korea.ac.kr
Current


임수현 (Suhyun Lim)

Ms (2017) DNN regularization using dropconnect in speech recognition
Contact suhyun0630 at ai.korea.ac.kr
Current


박지웅 (Jiwoong Park)

Ms (2016) Stacked denoising autoencoder for speech recognition
Contact jivvp at ai.korea.ac.kr
Current LG Electronics


탁민우(Minwoo Tahk)

Ms (2014) Parallel Baum-Welch algorithm for GPUs
Contact xkralsdn at nate.com
Current NHN


복휘(Buhui)

Ms (2014) Incremental lattice generation for continuous speech recognition
Contact greenbuhui at hotmail.com
Current Datatang


이병천(Byoungchun Lee)

Ms (2014) Parallel Viterbi algorithm using multi-core processors
Contact s4r4ng at naver.com
Current Softcamp


오상준(Sangjoon Oh)

Ms (2012) Speech enhancement in noisy environments for distant-talking speech recognition
Contact gradual at naver.com
Current LG Electronics


조선호(Sunho Cho)

Ms (2011) Segmented Viterbi algorithm for speech recognition
Contact sunho.cho at lge.com
Current LG Electronics


방용찬(Yongchan Bang)

Ms (2011) An improved speech visualization using formant frequency
Contact ycbang84 at gmail.com
Current LG Electronics


이시현(Sihyun Lee)

Ms (2010) 로봇 음원 위치 추적을 위한 소음제거 방법
Contact fullaheadkoko at nate.com
Current Samsung Electronics


권수혁(Soohyuk Kwon)

Ms (2010) Analysis of speaker recognition performance for various speaker enrollment methods and amount of speech data
Contact sbkwon99 at hotmail.com
Current Samsung SDI


최우진(Woojin Choi)

Ms (2010) Sound source localization using phase and sound pressure
Contact wjin.choi at lge.com
Current LG Electronics


공동현(Donghyun Kong)

Ms (2009) A study on speech visualization interface for language learner
Contact icharishkong at gmail.com
Current Yonsei University (진학)


양경철(Kyongchul Yang)

Ms (2009) Speech and music discrimination using spectral transition rate
Contact way2heaven at naver.com
Current Renault Samsung Motors


정재연(Jaeyoun Chung)

Ms (2007) A study on the effect of shadowed microphones for automatic sound source localization by robots
Contact tochan4 at gmail.com
Current LG Electronics


방규섭(Kyuseop Bang)

Ms (2006) Monophone distance를 이용한 효율적인 state clustering
Contact ksbang at hyundai.com
Current Hyundai Motor Company


유봉수(Bongsoo Yoo)

Ms (2005) 음성인식 성능향상을 위한 MMILST기반의 모델 적응 기법
Contact skylive99 at nate.com
Current Medison


김성아(Sung-A Kim)

Ms (2004) Data-driven attribute set generation for decision tree-based clustering
Contact ksa1220 at hotmail.com
Current Ajou University


이순규(Soonkyu Lee)

Ms (2003) Hidden Markov models을 이용한 viseme 인식
Contact sklee at dfocus.net
Current DFOCUS