Hyung Soon Kim

38 papers A 13B 1Misc 4Journal 11Unranked 9

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding. IEEE Access Sunchan Park, Hyung Soon Kim
2024	J	`jnl`	An experimental study of neural estimators of the mutual information between random vectors modeling power spectrum features. EURASIP J. Adv. Signal Process. Donghoon Shin, Hyung Soon Kim
2022	J	`jnl`	Attentive Pooling-Based Weighted Sum of Spectral Decay Rates for Blind Estimation of Reverberation Time. IEEE Signal Process. Lett. Min Sik Kim, Hyung Soon Kim
2017	—	`conf`	Multiresolution CNN for reverberant speech recognition. O-COCOSDA Sunchan Park, Yongwon Jeong, Hyung Soon Kim
2015	J	`jnl`	Weight-Space Viterbi Decoding Based Spectral Subtraction for Reverberant Speech Recognition. IEEE Signal Process. Lett. Sung Min Ban, Hyung Soon Kim
2014	J	`jnl`	Adaptation of Acoustic Models in Joint Speaker and Noise Space Using Bilinear Models. IEICE Trans. Inf. Syst. Yongwon Jeong, Hyung Soon Kim
2013	J	`jnl`	Speaker Adaptation Based on PARAFAC2 of Transformation Matrices for Continuous Speech Recognition. IEICE Trans. Inf. Syst. Yongwon Jeong, Sangjun Lim, Young Kuk Kim, Hyung Soon Kim
2012	—	`conf`	Speaking rate dependent multiple acoustic models using continuous frame rate normalization. APSIPA Sung Min Ban, Hyung Soon Kim
2011	A	`conf`	Joint Bilinear Transformation Space Based Maximum a posteriori Linear Regression Adaptation Using Prior with Variance Function. INTERSPEECH Hwa Jeon Song, Yunkeun Lee, Hyung Soon Kim
2010	—	`conf`	A robust target signal detector based on statistical models using binaural cross-similarity information. EUSIPCO Myung Jong Kim, Sung-Joo Lee, Hoirin Kim, Hyung Soon Kim
2010	J	`jnl`	New Speaker Adaptation Method Using 2-D PCA. IEEE Signal Process. Lett. Yongwon Jeong, Hyung Soon Kim
2010	A	`conf`	Speaker adaptation in transformation space using two-dimensional PCA. INTERSPEECH Yongwon Jeong, Young Rok Song, Hyung Soon Kim
2009	Misc	`conf`	A new method for speaker adaptation using bilinear model. ICASSP Hwa Jeon Song, Yongwon Jeong, Hyung Soon Kim
2009	J	`jnl`	Bilinear Model-Based Maximum Likelihood Linear Regression Speaker Adaptation Framework. IEEE Signal Process. Lett. Hwa Jeon Song, Hyung Soon Kim
2009	A	`conf`	Bilinear transformation space-based maximum likelihood linear regression frameworks. INTERSPEECH Hwa Jeon Song, Yongwon Jeong, Hyung Soon Kim
2009	A	`conf`	Voice activity detection using singular value decomposition-based filter. INTERSPEECH Hwa Jeon Song, Sung Min Ban, Hyung Soon Kim
2008	—	`conf`	Parallel Architecture for Sphere Decoder with Runtime Constraint. CCNC Jin Lee, Hyung Soon Kim, Sin-Chong Park
2007	B	`conf`	Speech/Music Discrimination for Robust Speech Recognition in Robots. RO-MAN Mu Yeol Choi, Hwa Jeon Song, Hyung Soon Kim
2006	—	`conf`	A New Approach for Speech/Music Discrimination Based on Cepstral Distance. ISCSLP Mu Yeol Choi, Seul-Han Park, Hwa Jeon Song, Hyung Soon Kim
2006	—	`conf`	Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments. TSD Hwa Jeon Song, Hyung Soon Kim
2006	—	`conf`	Performance Evaluation of Non-Keyword Modeling for Vocabulary-Independent Keyword Spotting. ISCSLP Young Kuk Kim, Hwa Jeon Song, Hyung Soon Kim
2005	A	`conf`	Eigen-environment based noise compensation method for robust speech recognition. INTERSPEECH Hwa Jeon Song, Hyung Soon Kim
2004	A	`conf`	A new score normalization method for speaker verification with virtual impostor model. INTERSPEECH Woo-Yong Choi, Jung Gon Kim, Hyung Soon Kim, Sung Bum Pan
2004	A	`conf`	Performance improvement of connected digit recognition using unsupervised fast speaker adaptation. INTERSPEECH Young Kuk Kim, Hwa Jeon Song, Hyung Soon Kim
2004	A	`conf`	Simultaneous estimation of weights of eigenvoices and bias compensation vector for rapid speaker adaptation. INTERSPEECH Hyung Soon Kim, Hwa Jeon Song
2003	A	`conf`	Performance improvement of rapid speaker adaptation based on eigenvoice and bias compensation. INTERSPEECH Jong Se Park, Hwa Jeon Song, Hyung Soon Kim
2002	A	`conf`	Computationally efficient time-scale modification of speech using 3 level clipping. INTERSPEECH Sung-Joo Lee, Hyung Soon Kim
2002	A	`conf`	Improving phone-level discrimination in LDA with subphone-level classes. INTERSPEECH Hwa Jeon Song, Hyung Soon Kim
2001	Misc	`conf`	Formant weighted cepstral feature for LSP-based speech recognition. ICASSP Ho Young Hur, Hyung Soon Kim
2000	J	`jnl`	A fast fractal decoding algorithm based on the selection of an initial image. IEEE Trans. Image Process. Yong Ho Moon, Hyung Soon Kim, Jae Ho Kim
2000	A	`conf`	Glottal parameters contributing to the perceotion of loud voices. INTERSPEECH Sopae Yi, Hyung Soon Kim, One Good Lee
2000	Misc	`conf`	Narrowband to wideband conversion of speech using GMM based transformation. ICASSP Kun-youl Park, Hyung Soon Kim
2000	A	`conf`	Predictive speaker adaptation based on least squares method. INTERSPEECH Woo-Yong Choi, Hyung Soon Kim
1999	J	`jnl`	A novel fast fractal decoding algorithm. Signal Process. Image Commun. Yong Ho Moon, Hyung Soon Kim, Yoo Shin Kim, Jae Ho Kim
1998	—	`conf`	Speech recognition in car noise environments using multiple models according to noise masking levels. ICSLP Myung Gyu Song, Hoi In Jung, Kab-Jong Shim, Hyung Soon Kim
1997	Misc	`conf`	Variable time-scale modification of speech using transient information. ICASSP Sung-Joo Lee, Hee-Dong Kim, Hyung Soon Kim
1994	J	`jnl`	A Korean Large Vocabulary Speech Recognition System for Automatic Telephone Number Query Service. Int. J. Pattern Recognit. Artif. Intell. Jun Mo Koo, Hyung Soon Kim, Chong Kwan Un
1990	—	`conf`	Speech recognition method based on the dual processing nature of speech perception. ICSLP Hyung Soon Kim, Chong Kwan Un