교수소개

김우일 사진

교수

김우일
직위(직급)
교수
전화번호
032-835-8459
이메일
wikim@inu.ac.kr
사이트
http://impress.inu.ac.kr
연구분야
음성인식, 신호처리, 패턴인식, 인공지능
세부내용

연구실적

 

<논문>

- A study on end-to-end speaker diarization system using single-label classification,Journal of the Acoustical Society of Korea ,42() ,6,2023.11.30

- A study on speech enhancement using complex-valued spectrum employing Feature map Dependent attention gate,Journal of the Acoustical Society of Korea ,42() ,6,PP.544~551 ,2023.11.30

- A study on skip-connection with time-frequency self-attention for improving speech enhancement based on complex-valued spectrum,Journal of the Acoustical Society of Korea ,42() ,2,PP.94~101 ,2023.03.31

- A study on deep neural speech enhancement in drone noise environment,Journal of the Acoustical Society of Korea ,41() ,3,PP.342~350 ,2022.05.31

- Class-GE2E: Speaker Verification Using Self-Attention and Transfer Learning with Loss Combination,Electronics ,11() ,6,2022.03.31

- A study on loss combination in time and frequency for effective speech enhancement based on complex-valued spectrum,Journal of the Acoustical Society of Korea ,41() ,1,PP.38~44 ,2022.01.31

- A study on combination of loss functions for effective mask-based speech enhancement in noisy environments,Journal of the Acoustical Society of Korea ,40() ,3,PP.234~240 ,2021.05.31

- Speaker Verification Employing Combinations of Self-Attention Mechanisms,Electronics ,9() ,12,2020.12.21

- Small-Footprint Wake Up Word Recognition in Noisy Environments Employing Competing-Words-Based Feature,Electronics ,9() ,12,2020.12.21

- I-vector similarity based speech segmentation for interested speaker to speaker diarization system,Journal of the Acoustical Society of Korea ,39() ,5,PP.461~467 ,2020.09.30

- Speaker verification system combining attention-long short term memory based speaker embedding and I-vector in far-field and noisy environments,Journal of the Acoustical Society of Korea ,39() ,2,PP.137~142 ,2020.03.01

- Deep neural network-hidden Markov model 하이브리드 구조의 모델을 사용한 사용자 정의 기동어 인식 시스템에 관한 연구,Journal of the Acoustical Society of Korea ,39() ,2,PP.131~136 ,2020.03.01

- 심층신경망 구조에 따른 구개인두부전증 환자 음성 인식 향상 연구,한국음향학회지 ,38() ,6,PP.703~709 ,2019.11.30

- 잡음 환경 음성 인식을 위한 심층 신경망 기반의 잡음 오염 함수 예측을 통한 음향 모델 적응 기법,한국음향학회지 ,38() ,1,PP.47~50 ,2019.01.31

- 잡음 환경에 효과적인 음성인식을 위한 특징 보상 이득 기반의 음성 향상 기법,한국음향학회지 ,38() ,1,PP.51~55 ,2019.01.31

- DNN-HMM 기반 시스템을 이용한 효과적인 구개인두부전증 환자 음성 인식,한국정보통신학회논문지 ,23() ,1,PP.33~38 ,2019.01.31

- 잡음 환경에 효과적인 음성 인식을 위한 Gaussian mixture model deep neural network 하이브리드 기반의 특징 보상,한국음향학회지 ,37() ,6,PP.506~511 ,2018.11.30

- 효과적인 음성 인식 평가를 위한 심층 신경망 기반의 음성 인식,한국정보통신학회논문지 ,21() ,12,PP.2291~2297 ,2017.12.31

- A Novel Discriminative Feature Extraction for Acoustic Scene Classification Using RNN Based Source Separation,IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS ,E100-D() ,12,PP.3041~3044 ,2017.12.01

- DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification,IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS ,E100-D() ,9,PP.2249~2252 ,2017.09.01

- Relative transfer function (RTF) estimation utilising peaks in time-domain RTF,ELECTRONICS LETTERS ,52() ,14,PP.1264~1266 ,2016.07.07

- Two-Microphone Generalized Sidelobe Canceller with Post-Filter Based Speech Enhancement in Composite Noise,ETRI JOURNAL ,38() ,2,PP.366~375 ,2016.04.01

- 음성 인식용 데이터베이스 검증시스템을 위한 새로운 음성 인식성능 지표,한국정보통신학회논문지 ,20() ,3,PP.464~470 ,2016.03.31

- 음성 특성 지표를 이용한 음성 인식 성능 예측,한국정보통신학회논문지 ,20() ,3,PP.471~476 ,2016.03.31

- 구개열 환자 발음 판별을 위한 특징 추출 방법 분석,정보과학회논문지 ,42() ,11,PP.1372~1379 ,2015.11.01

- Advanced parallel combined Gaussian mixture model based feature compensation integrated with iterative channel estimation,SPEECH COMMUNICATION ,73() ,PP.81~93 ,2015.10.01

- 모의 음성 모델을 이용한 효과적인 구개인두부전증 환자 음성 인식,한국정보통신학회논문지 ,19() ,5,PP.1243~1250 ,2015.05.31

- 미전사 음성 데이터베이스를 이용한 가우시안 혼합 모델 적응 기반의 음성 인식용 음향 모델 변환 기법,한국정보통신학회논문지 ,19() ,5,PP.1047~1054 ,2015.05.31

- 피보호자 모니터링 시스템을 위한 환경음 기반 상황 인식,한국정보통신학회논문지 ,19() ,2,PP.343~350 ,2015.02.28

- 이기종 음성 인식 시스템에 독립적으로 적용 가능한 특징 보상기반의 음성 향상 기법,한국정보통신학회논문지 ,18() ,10,PP.2367~2374 ,2014.10.31

- Noise estimation employing variational model composition for speech enhancement in time-varying noise conditions,Contemporary Engineering Sciences ,7() ,21-24,PP.1121~1129 ,2014.10.15

- Pre-Filtering Algorithm for Dual-Microphone Generalized Sidelobe Canceller Using General Transfer Function,IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS ,E97D() ,9,PP.2533~2536 ,2014.09.01

- Voice Activity Detection in Noisy Environments Based on Double-Combined Fourier Transform and Line Fitting,Scientific World Journal ,2014() ,2014.08.06

- 구개인두부전증 환자와 모의 음성의 모음과 자음 분석,한국정보통신학회논문지 ,18() ,7,PP.1740~1748 ,2014.07.31

- 시변 잡음에 강인한 음성 인식을 위한 PCA 기반의 Variational 모델 생성 기법,한국정보통신학회논문지 ,17() ,12,PP.2793~2799 ,2013.12.31

- An Energy-Effective MAC Protocol for Wireless Wearable Computer Systems,JICCE ,11() ,1,PP.7~11 ,2013.03.01

- A Novel Mask Estimation Method Employing Posterior-Based Representative Mean Estimate for Missing-Feature Speech Recognition,IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING ,19() ,5,PP.1434~1443 ,2011.07.01

- Variational noise model composition through model perturbation for robust speech recognition with time-varying background noise,SPEECH COMMUNICATION ,53() ,4,PP.451~464 ,2011.04.01

- Mask Classification for Missing-Feature Reconstruction for Robust Speech Recognition with Unknown Background Noise,SPEECH COMMUNICATION ,53() ,1,PP.1~11 ,2011.01.01

- Robust Emotional Stressed Speech Detection Using Weighted Frequency Subbands,EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING ,2011.01.01

- Missing-Feature Reconstruction by Leveraging Temporal Spectral Correlation for Robust Speech Recognition in Background Noise Conditions,IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING ,18() ,8,PP.2111~2120 ,2010.11.01

- Automatic voice onset time detection for unvoiced stops (/p/,/t/,/k/) with application to accent classification,SPEECH COMMUNICATION ,52() ,10,PP.777~789 ,2010.10.01

- Phonetic Distance Based Confidence Measure,IEEE SIGNAL PROCESSING LETTERS ,17() ,2,PP.117~120 ,2010.02.01