default search action
Hoirin Kim
Hoi Rin Kim
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c43]Kangwook Jang, Sungnyun Kim, Hoirin Kim:
STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models. ICASSP 2024: 10721-10725 - [i23]Hyun Myung Kim, Kangwook Jang, Hoirin Kim:
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection. CoRR abs/2406.16716 (2024) - [i22]Sungnyun Kim, Kangwook Jang, Sangmin Bae, Hoirin Kim, Se-Young Yun:
Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition. CoRR abs/2407.03563 (2024) - 2023
- [c42]Kangwook Jang, Sungnyun Kim, Se-Young Yun, Hoirin Kim:
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation. INTERSPEECH 2023: 316-320 - [c41]Myunghun Jung, Hoirin Kim:
AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination. INTERSPEECH 2023: 3924-3928 - [i21]Kangwook Jang, Sungnyun Kim, Se-Young Yun, Hoirin Kim:
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation. CoRR abs/2305.11685 (2023) - [i20]Kangwook Jang, Sungnyun Kim, Hoirin Kim:
STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models. CoRR abs/2312.09040 (2023) - 2022
- [j31]Yeunju Choi
, Youngmoon Jung
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech. IEEE Access 10: 52621-52629 (2022) - [c40]Ji Sub Um, Yeunju Choi, Hoi Rin Kim:
ACNN-VC: Utilizing Adaptive Convolution Neural Network for One-Shot Voice Conversion. INTERSPEECH 2022: 2998-3002 - [c39]Youngsik Eom, Yeonghyeon Lee, Ji Sub Um, Hoi Rin Kim:
Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck. INTERSPEECH 2022: 3568-3572 - [c38]Yeonghyeon Lee, Kangwook Jang, Jahyun Goo, Youngmoon Jung, Hoi Rin Kim:
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Models. INTERSPEECH 2022: 3588-3592 - [c37]Myunghun Jung, Hoi Rin Kim:
Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings. INTERSPEECH 2022: 5170-5174 - [i19]Myunghun Jung, Hoirin Kim:
Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings. CoRR abs/2203.16080 (2022) - [i18]Youngsik Eom, Yeonghyeon Lee, Ji Sub Um, Hoirin Kim:
Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck. CoRR abs/2204.01387 (2022) - [i17]Yeonghyeon Lee, Kangwook Jang, Jahyun Goo, Youngmoon Jung, Hoirin Kim:
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning. CoRR abs/2207.00555 (2022) - [i16]Myunghun Jung, Hoirin Kim:
Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination. CoRR abs/2210.14564 (2022) - 2021
- [c36]Seong Min Kye, Joon Son Chung, Hoirin Kim:
Supervised Attention for Speaker Recognition. SLT 2021: 286-293 - [c35]Yeunju Choi, Youngmoon Jung, Hoirin Kim:
Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning with Spoofing Detection and Spoofing Type Classification. SLT 2021: 462-469 - 2020
- [j30]Youngmoon Jung
A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments. IEEE Access 8: 175448-175466 (2020) - [j29]Hyungjun Lim
Interlayer Selective Attention Network for Robust Personalized Wake-Up Word Detection. IEEE Signal Process. Lett. 27: 126-130 (2020) - [j28]Hyungjun Lim
Cross-Informed Domain Adversarial Training for Noise-Robust Wake-Up Word Detection. IEEE Signal Process. Lett. 27: 1769-1773 (2020) - [j27]Ji H. Kim
Single-Variable-Input Active Sidelobe Suppression Method for Synthesized Magnetic Field Focusing Technology and Its Optimization. IEEE Trans. Ind. Electron. 67(11): 9813-9823 (2020) - [c34]Joohyung Lee, Youngmoon Jung, Myunghun Jung, Hoirin Kim:
Dynamic Noise Embedding: Noise Aware Training and Adaptation for Speech Enhancement. APSIPA 2020: 739-746 - [c33]Myunghun Jung, Youngmoon Jung, Jahyun Goo, Hoirin Kim:
Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification Using CTC-Based Soft VAD and Global Query Attention. INTERSPEECH 2020: 931-935 - [c32]Youngmoon Jung, Seong Min Kye, Yeunju Choi, Myunghun Jung, Hoirin Kim:
Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances. INTERSPEECH 2020: 1501-1505 - [c31]Yeunju Choi, Youngmoon Jung, Hoirin Kim:
Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling. INTERSPEECH 2020: 1743-1747 - [c30]Seong Min Kye, Youngmoon Jung, Haebeom Lee, Sung Ju Hwang, Hoirin Kim:
Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs. INTERSPEECH 2020: 2982-2986 - [c29]Joohyung Lee, Youngmoon Jung, Hoirin Kim:
Dual Attention in Time and Frequency Domain for Voice Activity Detection. INTERSPEECH 2020: 3670-3674 - [i15]Seong Min Kye, Haebeom Lee, Hoirin Kim, Sung Ju Hwang:
Transductive Few-shot Learning with Meta-Learned Confidence. CoRR abs/2002.12017 (2020) - [i14]Seong Min Kye, Youngmoon Jung, Haebeom Lee, Sung Ju Hwang, Hoirin Kim:
Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs. CoRR abs/2004.02863 (2020) - [i13]Youngmoon Jung, Seong Min Kye, Yeunju Choi, Myunghun Jung, Hoirin Kim:
Multi-Scale Aggregation Using Feature Pyramid Module for Text-Independent Speaker Verification. CoRR abs/2004.03194 (2020) - [i12]Myunghun Jung, Youngmoon Jung, Jahyun Goo, Hoirin Kim:
Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention. CoRR abs/2005.03867 (2020) - [i11]Sunghee Jung, Hoirin Kim:
Pitchtron: Towards audiobook generation from ordinary people's voices. CoRR abs/2005.10456 (2020) - [i10]Sunghee Jung, Hoirin Kim:
Neural voice cloning with a few low-quality samples. CoRR abs/2006.06940 (2020) - [i9]Yeunju Choi, Youngmoon Jung, Hoirin Kim:
Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classification. CoRR abs/2007.08267 (2020) - [i8]Yeunju Choi, Youngmoon Jung, Hoirin Kim:
Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling. CoRR abs/2008.03710 (2020) - [i7]Youngmoon Jung, Yeunju Choi, Hyungjun Lim, Hoirin Kim:
A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments. CoRR abs/2010.02477 (2020) - [i6]Yeunju Choi, Youngmoon Jung, Youngjoo Suh, Hoirin Kim:
Perceptually Guided End-to-End Text-to-Speech. CoRR abs/2011.01174 (2020) - [i5]Seong Min Kye, Joon Son Chung, Hoirin Kim:
Supervised attention for speaker recognition. CoRR abs/2011.05189 (2020)
2010 – 2019
- 2019
- [j26]Ji H. Kim
2-D Synthesized Magnetic Field Focusing Technology With Loop Coils Distributed in a Rectangular Formation. IEEE Trans. Ind. Electron. 66(7): 5558-5566 (2019) - [c28]Youngmoon Jung, Yeunju Choi, Hoirin Kim:
Self-Adaptive Soft Voice Activity Detection Using Deep Neural Networks for Robust Speaker Verification. ASRU 2019: 365-372 - [c27]Myunghun Jung, Hyungjun Lim, Jahyun Goo, Youngmoon Jung, Hoirin Kim:
Additional Shared Decoder on Siamese Multi-View Encoders for Learning Acoustic Word Embeddings. ASRU 2019: 629-636 - [c26]Youngmoon Jung, Younggwan Kim, Hyungjun Lim
Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification. INTERSPEECH 2019: 4030-4034 - [i4]Youngmoon Jung, Younggwan Kim, Hyungjun Lim, Yeunju Choi, Hoirin Kim:
Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification. CoRR abs/1906.08333 (2019) - [i3]Youngmoon Jung, Yeunju Choi, Hoirin Kim:
Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification. CoRR abs/1909.11886 (2019) - [i2]Myunghun Jung, Hyungjun Lim
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings. CoRR abs/1910.00341 (2019) - 2018
- [j25]Younggwan Kim
Learning Self-Informed Feature Contribution for Deep Learning-Based Acoustic Modeling. IEEE ACM Trans. Audio Speech Lang. Process. 26(11): 2204-2214 (2018) - [c25]Youngmoon Jung, Younggwan Kim, Yeunju Choi, Hoirin Kim:
Joint Learning Using Denoising Variational Autoencoders for Voice Activity Detection. INTERSPEECH 2018: 1210-1214 - [i1]Hyungjun Lim
Learning acoustic word embeddings with phonetically associated triplet network. CoRR abs/1811.02736 (2018) - 2017
- [c24]Hyungjun Lim
CNN-based bottleneck feature for noise robust query-by-example spoken term detection. APSIPA 2017: 1278-1281 - [c23]Younggwan Kim, Hyungjun Lim
Deep Least Squares Regression for Speaker Adaptation. INTERSPEECH 2017: 729-733 - [c22]Youngmoon Jung, Younggwan Kim, Hyungjun Lim, Hoirin Kim:
Linear-scale filterbank for deep neural network-based voice activity detection. O-COCOSDA 2017: 1-5 - [c21]Youngjoo Suh, Younggwan Kim, Hyungjun Lim
Development of distant multi-channel speech and noise databases for speech recognition by in-door conversational robots. O-COCOSDA 2017: 1-4 - 2016
- [c20]Hyungjun Lim
Cross-acoustic transfer learning for sound event classification. ICASSP 2016: 2504-2508 - [c19]Myung Jong Kim, Jun Wang, Hoirin Kim:
Dysarthric Speech Recognition Using Kullback-Leibler Divergence-Based Hidden Markov Model. INTERSPEECH 2016: 2671-2675 - [c18]Jahyun Goo, Younggwan Kim, Hyungjun Lim
Speaker Normalization Through Feature Shifting of Linearly Transformed i-Vector. INTERSPEECH 2016: 3489-3493 - 2015
- [j24]Younggwan Kim, Myung Jong Kim, Hoirin Kim:
Scaled norm-based Euclidean projection for sparse speaker adaptation. EURASIP J. Adv. Signal Process. 2015: 102 (2015) - [j23]Youngjoo Suh, Hoirin Kim:
Probabilistic Class Histogram Equalization Based on Posterior Mean Estimation for Robust Speech Recognition. IEEE Signal Process. Lett. 22(12): 2421-2424 (2015) - [j22]Myung Jong Kim, Younggwan Kim, Hoirin Kim:
Automatic Intelligibility Assessment of Dysarthric Speech Using Phonologically-Structured Sparse Linear Model. IEEE ACM Trans. Audio Speech Lang. Process. 23(4): 694-704 (2015) - [c17]Myung Jong Kim, Joohong Yoo, Younggwan Kim, Hoirin Kim:
Speech emotion classification using tree-structured sparse logistic regression. INTERSPEECH 2015: 1541-1545 - [c16]Hyungjun Lim, Myung Jong Kim, Hoirin Kim:
Robust sound event classification using LBP-HOG based bag-of-audio-words feature representation. INTERSPEECH 2015: 3325-3329 - 2014
- [j21]Youngjoo Suh, Hoirin Kim:
Discriminative likelihood score weighting based on acoustic-phonetic classification for speaker identification. EURASIP J. Adv. Signal Process. 2014: 126 (2014) - [c15]Younggwan Kim, Hoirin Kim:
Constrained MLE-based speaker adaptation with L1 regularization. ICASSP 2014: 6369-6373 - 2013
- [c14]Myung Jong Kim, Younggwan Kim, Seungki Hong, Hoirin Kim:
ROBUST detection of infant crying in adverse environments using weighted segmental two-dimensional linear frequency cepstral coefficients. ICME Workshops 2013: 1-4 - [c13]Myung Jong Kim, Joohong Yoo, Hoirin Kim:
Dysarthric speech recognition using dysarthria-severity-dependent and speaker-adaptive models. INTERSPEECH 2013: 3622-3626 - 2012
- [j20]Youngjoo Suh, Hoirin Kim:
Multiple Acoustic Model-Based Discriminative Likelihood Ratio Weighting for Voice Activity Detection. IEEE Signal Process. Lett. 19(8): 507-510 (2012) - [j19]Myung Jong Kim, Hoirin Kim:
Audio-Based Objectionable Content Detection Using Discriminative Transforms of Time-Frequency Dynamics. IEEE Trans. Multim. 14(5): 1390-1400 (2012) - [c12]Myung Jong Kim, Hoirin Kim:
Automatic Assessment of Dysarthric Speech Intelligibility Based on Selected Phonetic Quality Features. ICCHP (2) 2012: 447-450 - [c11]Myung Jong Kim, Hoirin Kim:
Combination of Multiple Speech Dimensions for Automatic Assessment of Dysarthric Speech Intelligibility. INTERSPEECH 2012: 1323-1326 - 2011
- [j18]Younggwan Kim, Youngjoo Suh, Hoirin Kim:
Reliable likelihood ratios for statistical model-based voice activity detector with low false-alarm rate. EURASIP J. Adv. Signal Process. 2011: 31 (2011) - [c10]Myung Jong Kim, Hoirin Kim:
Automatic extraction of pornographic contents using radon transform based audio features. CBMI 2011: 205-210 - 2010
- [j17]Youngjoo Suh, Hoirin Kim:
Histogram Equalization to Model Adaptation for Robust Speech Recognition. EURASIP J. Adv. Signal Process. 2010 (2010) - [j16]Youngjoo Suh, Hoirin Kim:
Cepstral Domain Feature Extraction Utilizing Entropic Distance-Based Filterbank. IEICE Trans. Inf. Syst. 93-D(2): 392-394 (2010) - [j15]Suk-Bong Kwon, Hoirin Kim:
Utterance Verification Using State-Level Log-Likelihood Ratio with Frame and State Selection. IEICE Trans. Inf. Syst. 93-D(3): 647-650 (2010) - [j14]Jae Sam Yoon, Ji Hun Park, Hong Kook Kim, Hoirin Kim:
Acoustic Model Combination Incorporated With Mask-Based Multi-Channel Source Separation for Automatic Speech Recognition. IEEE J. Sel. Top. Signal Process. 4(5): 772-784 (2010) - [j13]Sungtak Kim, Miyoung Ji, Hoirin Kim:
Robust speaker recognition based on filtering in autocorrelation domain and sub-band feature recombination. Pattern Recognit. Lett. 31(7): 593-599 (2010) - [c9]Myung Jong Kim, Sung-Joo Lee, Hoirin Kim, Hyung Soon Kim:
A robust target signal detector based on statistical models using binaural cross-similarity information. EUSIPCO 2010: 2082-2086 - [c8]Myung Jong Kim, Younggwan Kim, JaeDeok Lim, Hoirin Kim:
Automatic detection of malicious sound using segmental two-dimensional mel-frequency cepstral coefficients and histograms of oriented gradients. ACM Multimedia 2010: 887-890
2000 – 2009
- 2009
- [j12]Youngjoo Suh, Hoirin Kim:
Environmental Model Adaptation Based on Histogram Equalization. IEEE Signal Process. Lett. 16(4): 264-267 (2009) - [c7]Youngjoo Suh, Hoirin Kim:
The effectiveness of histogram equalization on environmental model adaptation. ICASSP 2009: 4389-4392 - 2008
- [j11]Youngjoo Suh, Hoirin Kim, Munchurl Kim:
Histogram Equalization Utilizing Window-Based Smoothed CDF Estimation for Feature Compensation. IEICE Trans. Inf. Syst. 91-D(8): 2199-2202 (2008) - [j10]Suk-Bong Kwon, Hoirin Kim:
Utterance Verification Using Word Voiceprint Models Based on Probabilistic Distributions of Phone-Level Log-Likelihood Ratio and Phone Duration. IEICE Trans. Inf. Syst. 91-D(11): 2746-2750 (2008) - [j9]Mikyong Ji, Sungtak Kim, Hoirin Kim, Ho-Sub Yoon:
Text-Independent Speaker Identification using Soft Channel Selection in Home Robot Environments. IEEE Trans. Consumer Electron. 54(1): 140-144 (2008) - 2007
- [j8]Youngjoo Suh, Sungtak Kim, Hoirin Kim:
Compensating Acoustic Mismatch Using Class-Based Histogram Equalization for Robust Speech Recognition. EURASIP J. Adv. Signal Process. 2007 (2007) - [j7]Sangbae Jeong, Hoirin Kim, Minsoo Hahn:
Response Time Reduction of Speech Recognizers Using Single Gaussians. IEICE Trans. Inf. Syst. 90-D(5): 868-871 (2007) - [j6]Mikyong Ji, Sungtak Kim, Hoirin Kim:
Text-Independent Speaker Identification in a Distant-Talking Multi-Microphone Environment. IEICE Trans. Inf. Syst. 90-D(11): 1892-1895 (2007) - [j5]Sungtak Kim, Mikyong Ji, Youngjoo Suh, Hoirin Kim:
Noise Robust Speaker Identification Using Sub-Band Weighting in Multi-Band Approach. IEICE Trans. Inf. Syst. 90-D(12): 2110-2114 (2007) - [j4]Youngjoo Suh, Mikyong Ji, Hoirin Kim:
Probabilistic Class Histogram Equalization for Robust Speech Recognition. IEEE Signal Process. Lett. 14(4): 287-290 (2007) - [c6]Mikyong Ji, Sungtak Kim, Hoirin Kim, Keun-Chang Kwak, Young-Jo Cho:
Reliable Speaker Identification Using Multiple Microphones in Ubiquitous Robot Companion Environment. RO-MAN 2007: 673-677 - 2006
- [j3]Sung Ho Jin, Tae Meon Bae, Yong Man Ro
Intelligent broadcasting system and services for personalized semantic contents consumption. Expert Syst. Appl. 31(1): 164-173 (2006) - [j2]Mansoo Park, Hoirin Kim, Yong Man Ro
Frequency Filtering for a Highly Robust Audio Fingerprinting Scheme in a Real-Noise Environment. IEICE Trans. Inf. Syst. 89-D(7): 2324-2327 (2006) - [j1]Youngjoo Suh, Hoirin Kim, Minsoo Hahn, Yong-Ju Lee:
Soft Counting Poisson Mixture Model-Based Polling Method for Speech/Nonspeech Classification. IEICE Trans. Inf. Syst. 89-D(12): 2994-2997 (2006) - [c5]Sangho Kim, Sungtak Kim, Suk-Bong Kwon, Hoirin Kim:
A Music Summarization Scheme using Tempo Tracking and Two Stage Clustering. MMSP 2006: 225-228 - [c4]Mikyong Ji, Sungtak Kim, Hoirin Kim:
Composite Decision by Bayesian Inference in Distant-Talking Speech Recognition. TSD 2006: 463-470 - 2005
- [c3]Mansoo Park, Hoirin Kim, Dong-Ho Shin, Seung Hyun Yang:
Audio Fingerprinting Scheme by Temporal Filtering for Audio Identification Immune to Channel-Distortion. AIRS 2005: 528-533 - 2004
- [c2]Sungtak Kim, Hoirin Kim:
Reliable Unseen Model Prediction for Vocabulary-Independent Speech Recognition. Australian Conference on Artificial Intelligence 2004: 599-609 - 2003
- [c1]Kyuhong Kim, Hoirin Kim:
A Fast Utterance Verification Method for OOV Rejection. SIP 2003: 119-122
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-08-25 19:04 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: