Joon-Hyuk Chang

ORCID

Publication Activity (10 Years)

Years Active: 2000-2024
Publications (10 Years): 107

Top Venues

INTERSPEECH

IEEE Access

ICASSP

IEEE ACM Trans. Audio Speech Lang. Process.

Publications

Chee-Hyun Park, Joon-Hyuk Chang
Robust Time-of-Arrival-Based Splitting Mean Moving Object Localization. IEEE Signal Process. Lett. 31 (2024)
Jae-Hong Lee, Joon-Hyuk Chang
Partitioning Attention Weight: Mitigating Adverse Effect of Incorrect Pseudo-Labels for Self-Supervised ASR. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Mun-Hak Lee, Sang-Eon Lee, Ji-Eun Choi, Joon-Hyuk Chang
Cross-Modal Learning for CTC-Based ASR: Leveraging CTC-Bertscore and Sequence-Level Training. ASRU (2023)
Chee-Hyun Park, Joon-Hyuk Chang
Robust Localization Method Based on Non-Parametric Probability Density Estimation. IEEE Access 11 (2023)
Ju-Seok Seong, Jeong-Hwan Choi, Jehyun Kyung, Ye-Rin Jeoung, Joon-Hyuk Chang
Noise-Aware Target Extension with Self-Distillation for Robust Speech Recognition. ICASSP (2023)
Da-Hee Yang, Joon-Hyuk Chang
Selective Film Conditioning with CTC-Based ASR Probability for Speech Enhancement. ICASSP (2023)
Pil Moo Byun, Jeong-Hwan Choi, Joon-Hyuk Chang
Class Activation Mapping-Driven Data Augmentation: Masking Significant Regions for Enhanced Acoustic Scene Classification. WASPAA (2023)
Jehyun Kyung, Jeong-Hwan Choi, Ju-Seok Seong, Ye-Rin Jeoung, Joon-Hyuk Chang
A Multi-modal Teacher-student Framework for Improved Blood Pressure Estimation. EMBC (2023)
Jin-Seong Choi, Jae-Hong Lee, Chae-Won Lee, Joon-Hyuk Chang
M-CTRL: A Continual Representation Learning Framework with Slowly Improving Past Pre-Trained Model. ICASSP (2023)
Ji-Hwan Mo, Jae-Jin Jeon, Mun-Hak Lee, Joon-Hyuk Chang
Knowledge Distillation From Offline to Streaming Transducer: Towards Accurate and Fast Streaming Model by Matching Alignments. ASRU (2023)
Sohee Jang, Jiye Kim, Yeon-Ju Kim, Joon-Hyuk Chang
Adaptive Time-Scale Modification for Improving Speech Intelligibility Based On Phoneme Clustering For Streaming Services. ICASSP (2023)
Da-Hee Yang, Joon-Hyuk Chang
Attention-based latent features for jointly trained end-to-end automatic speech recognition with modified speech enhancement. J. King Saud Univ. Comput. Inf. Sci. 35 (3) (2023)
Da-Hee Yang, Joon-Hyuk Chang
Towards Robust Packet Loss Concealment System With ASR-Guided Representations. ASRU (2023)
Pil Moo Byun, Joon-Hyuk Chang
Effective Masking Shapes Based Robust Data Augmentation for Acoustic Scene Classification. IC-NIDC (2023)
Donghyun Kim, Joon-Hyuk Chang
Restoration of Face Mask-Induced Speech Intelligibility Degradation Via Neural Bandwidth Extension. IC-NIDC (2023)
Jae-Hong Lee, Do-Hee Kim, Joon-Hyuk Chang
AWMC: Online Test-Time Adaptation Without Mode Collapse for Continual Adaptation. ASRU (2023)
Yoon-Ah Park, Joon-Hyuk Chang
Audio Captioning Using Semantic Alignment Enhancer. IC-NIDC (2023)
Ye-Rin Jeoung, Joon-Young Yang, Jeong-Hwan Choi, Joon-Hyuk Chang
Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads. CoRR (2023)
Jae-Hong Lee, Dong-Hyun Kim, Joon-Hyuk Chang
Repackagingaugment: Overcoming Prediction Error Amplification in Weight-Averaged Speech Recognition Models Subject to Self-Training. ICASSP (2023)
Da-Hee Yang, Donghyun Kim, Joon-Hyuk Chang
Masked Frequency Modeling for Improving Packet Loss Concealment in Speech Transmission Systems. WASPAA (2023)
Ye-Rin Jeoung, Joon-Young Yang, Jeong-Hwan Choi, Joon-Hyuk Chang
Improving Transformer-Based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads. ICASSP (2023)
Jeong-Hwan Choi, Jehyun Kyung, Ju-Seok Seong, Ye-Rin Jeoung, Joon-Hyuk Chang
Extending Self-Distilled Self-Supervised Learning For Semi-Supervised Speaker Verification. ASRU (2023)
Jae-Heung Cho, Joon-Hyuk Chang
CAN2V: Can-Bus Data-Based Seq2seq Model for Vehicle Velocity Prediction. ICASSP (2023)
Joo-Hyun Lee, Joon-Hyuk Chang, Jae-Mo Yang, Han-Gil Moon
NAS-TasNet: Neural Architecture Search for Time-Domain Speech Separation. IEEE Access 10 (2022)
Jaeuk Lee, Joon-Hyuk Chang
One-Shot Speaker Adaptation Based on Initialization by Generative Adversarial Networks for TTS. INTERSPEECH (2022)
Joon-Young Yang, Joon-Hyuk Chang
Task-Specific Optimization of Virtual Channel Linear Prediction-Based Speech Dereverberation Front-End for Far-Field Speaker Verification. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Jeong-Hwan Choi, Joon-Young Yang, Ye-Rin Jeoung, Joon-Hyuk Chang
HYU Submission for the SASV Challenge 2022: Reforming Speaker Embeddings with Spoofing-Aware Conditioning. INTERSPEECH (2022)
Won-Gook Choi, Joon-Hyuk Chang
Confidence Regularized Entropy for Polyphonic Sound Event Detection. DCASE (2022)
Jaeuk Lee, Joon-Hyuk Chang
Advanced Speaker Embedding with Predictive Variance of Gaussian Distribution for Speaker Adaptation in TTS. INTERSPEECH (2022)
Dong-Hyun Kim, Jae-Hong Lee, Ji-Hwan Mo, Joon-Hyuk Chang
W2V2-Light: A Lightweight Version of Wav2vec 2.0 for Automatic Speech Recognition. INTERSPEECH (2022)
Joon-Young Yang, Joon-Hyuk Chang
VACE-WPE: Virtual Acoustic Channel Expansion Based on Neural Networks for Weighted Prediction Error-Based Speech Dereverberation. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Chee-Hyun Park, Joon-Hyuk Chang
Robust Localization Based on Mixed-Norm Minimization Criterion. IEEE Access 10 (2022)
Jae-Hong Lee, Chae Won Lee, Jin-Seong Choi, Joon-Hyuk Chang, Woo Kyeong Seong, Jeonghan Lee
CTRL: Continual Representation Learning to Transfer Information of Pre-trained for WAV2VEC 2.0. INTERSPEECH (2022)
Chee-Hyun Park, Joon-Hyuk Chang
Revisiting Skipped Filter and Development of Robust Localization Method Based on Variational Bayesian Gaussian Mixture Algorithm. IEEE Trans. Signal Process. 70 (2022)
Won-Gook Choi, Joon-Hyuk Chang, Jae-Mo Yang, Han-Gil Moon
Instance-level loss based multiple-instance learning for acoustic scene classification. CoRR (2022)
Jeong-Hwan Choi, Joon-Young Yang, Ye-Rin Jeoung, Joon-Hyuk Chang
Improved CNN-Transformer using Broadcasted Residual Learning for Text-Independent Speaker Verification. INTERSPEECH (2022)
Mun-Hak Lee, Joon-Hyuk Chang, Sang-Eon Lee, Ju-Seok Seong, Chanhee Park, Haeyoung Kwon
Regularizing Transformer-based Acoustic Models by Penalizing Attention Weights. INTERSPEECH (2022)
Min-Kyung Kim, Joon-Hyuk Chang
Adversarial and Sequential Training for Cross-lingual Prosody Transfer TTS. INTERSPEECH (2022)
Da-Hee Yang, Joon-Hyuk Chang
FiLM Conditioning with Enhanced Feature to the Transformer-based End-to-End Noisy Speech Recognition. INTERSPEECH (2022)
Joon-Hyuk Chang, Won-Gook Choi
Convolutional Recurrent Neural Network with Auxiliary Stream for Robust Variable-Length Acoustic Scene Classification. INTERSPEECH (2022)
Moa Lee, Junmo Lee, Joon-Hyuk Chang
Non-Autoregressive Fully Parallel Deep Convolutional Neural Speech Synthesis. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Jeong-Hwan Choi, Joon-Hyuk Chang
Supervised Learning Approach for Explicit Spatial Filtering of Speech. IEEE Signal Process. Lett. 29 (2022)
Joo-Hyun Lee, Jeong-Hwan Choi, Pil Moo Byun, Joon-Hyuk Chang
Multi-Scale Architecture and Device-Aware Data-Random-Drop Based Fine-Tuning Method for Acoustic Scene Classification. DCASE (2022)
Mun-Hak Lee, Joon-Hyuk Chang
Knowledge Distillation from Language Model to Acoustic Model: A Hierarchical Multi-Task Learning Approach. ICASSP (2022)
Jung-Hee Kim, Jeong-Hwan Choi, Jinyoung Son, Gyeong-Su Kim, Jihwan Park, Joon-Hyuk Chang
MIMO Noise Suppression Preserving Spatial Cues for Sound Source Localization in Mobile Robot. ISCAS (2021)
Jeong-Hwan Choi, Joon-Young Yang, Joon-Hyuk Chang
Short-Utterance Embedding Enhancement Method Based on Time Series Forecasting Technique for Text-Independent Speaker Verification. ASRU (2021)
Mun-Hak Lee, Joon-Hyuk Chang
Deep Neural Network Calibration for E2E Speech Recognition System. Interspeech (2021)
Seong-Chel Park, Kwan-Ho Park, Joon-Hyuk Chang
Luminance-Degradation Compensation Based on Multistream Self-Attention to Address Thin-Film Transistor-Organic Light Emitting Diode Burn-In. Sensors 21 (9) (2021)
Tae-Jun Park, Joon-Hyuk Chang
Deep Q-network-based noise suppression for robust speech recognition. Turkish J. Electr. Eng. Comput. Sci. 29 (5) (2021)
Sung-Woong Hwang, Joon-Hyuk Chang
Document-Level Neural TTS Using Curriculum Learning and Attention Masking. IEEE Access 9 (2021)
Jin-Young Son, Joon-Hyuk Chang
Attention-Based Joint Training of Noise Suppression and Sound Event Detection for Noise-Robust Classification. Sensors 21 (20) (2021)
Jae-Hong Lee, Joon-Hyuk Chang
Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs. CoRR (2021)
Jaeuk Lee, Jiye Kim, Joon-Hyuk Chang
Zero-Shot Voice Cloning Using Variational Embedding with Attention Mechanism. IC-NIDC (2021)
Mun-Hak Lee, Joon-Hyuk Chang
Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach. CoRR (2021)
Chee-Hyun Park, Joon-Hyuk Chang
Robust Localization Employing Weighted Least Squares Method Based on MM Estimator and Kalman Filter With Maximum Versoria Criterion. IEEE Signal Process. Lett. 28 (2021)
Chee-Hyun Park, Joon-Hyuk Chang
Modified MM Algorithm and Bayesian Expectation Maximization-Based Robust Localization Under NLOS Contaminated Environments. IEEE Access 9 (2021)
Song-Kyu Park, Joon-Hyuk Chang
Multi-TALK: Multi-Microphone Cross-Tower Network for Jointly Suppressing Acoustic Echo and Background Noise. Sensors 20 (22) (2020)
Joon-Young Yang, Joon-Hyuk Chang
Virtual Acoustic Channel Expansion Based on Neural Networks for Weighted Prediction Error-Based Speech Dereverberation. INTERSPEECH (2020)
Jung-Hee Kim, Jeong-Hwan Choi, Sang Won Nam, Joon-Hyuk Chang
Delayless Block Individual-Weighting-Factors Sign Subband Adaptive Filters With an Improved Band-Dependent Variable Step-Size. IEEE Access 8 (2020)
Chee-Hyun Park, Joon-Hyuk Chang
Robust Localization Based on ML-Type, Multi-Stage ML-Type, and Extrapolated Single Propagation UKF Methods Under Mixed LOS/NLOS Conditions. IEEE Trans. Wirel. Commun. 19 (9) (2020)
Inyoung Hwang, Joon-Hyuk Chang
End-to-End Speech Endpoint Detection Utilizing Acoustic and Language Modeling Knowledge for Online Low-Latency Speech Recognition. IEEE Access 8 (2020)
Chee-Hyun Park, Joon-Hyuk Chang
Robust range estimation algorithm based on hyper-tangent loss function. IET Signal Process. 14 (5) (2020)
Kwang-Sub Song, Ku-young Chung, Joon-Hyuk Chang
Cuffless Deep Learning-Based Blood Pressure Estimation for Smart Wristwatches. IEEE Trans. Instrum. Meas. 69 (7) (2020)
Kyoung Jin Noh, Joon-Hyuk Chang
Joint Optimization of Deep Neural Network-Based Dereverberation and Beamforming for Sound Event Detection in Multi-Channel Environments. Sensors 20 (7) (2020)
Kyoung Jin Noh, Joon-Hyuk Chang
Deep neural network ensemble for reducing artificial noise in bandwidth extension. Digit. Signal Process. 102 (2020)
Jung-Hee Kim, Joon-Hyuk Chang
Attention Wave-U-Net for Acoustic Echo Cancellation. INTERSPEECH (2020)
Chee-Hyun Park, Joon-Hyuk Chang
WLS Localization Using Skipped Filter, Hampel Filter, Bootstrapping and Gaussian Mixture EM in LOS/NLOS Conditions. IEEE Access 7 (2019)
Moa Lee, Jee-Hye Lee, Joon-Hyuk Chang
Ensemble of jointly trained deep neural network-based acoustic models for reverberant speech recognition. Digit. Signal Process. 85 (2019)
Chee-Hyun Park, Joon-Hyuk Chang
Shrinkage sinusoidal phase estimation based on spherical simplex unscented transform and bootstrap method. Trans. Emerg. Telecommun. Technol. 30 (7) (2019)
Junmo Lee, Kwang-Sub Song, Kyoung Jin Noh, Tae-Jun Park, Joon-Hyuk Chang
DNN based multi-speaker speech synthesis with temporal auxiliary speaker ID embedding. ICEIC (2019)
Jihwan Park, Joon-Hyuk Chang
State-Space Microphone Array Nonlinear Acoustic Echo Cancellation Using Multi-Microphone Near-End Speech Covariance. IEEE ACM Trans. Audio Speech Lang. Process. 27 (10) (2019)
Chee-Hyun Park, Joon-Hyuk Chang
Robust Shrinkage Range Estimation Algorithms Based on Hampel and Skipped Filters. Wirel. Commun. Mob. Comput. 2019 (2019)
Joon-Young Yang, Joon-Hyuk Chang
Joint Optimization of Neural Acoustic Beamforming and Dereverberation with x-Vectors for Robust Speaker Verification. INTERSPEECH (2019)
Kwang-Sub Song, Joon-Hyuk Chang
Smart Wristwatches Employing Finger-Conducted Voice Transmission System. IEEE Trans. Ind. Informatics 15 (2) (2019)
Chee-Hyun Park, Joon-Hyuk Chang
Robust LMedS-Based WLS and Tukey-Based EKF Algorithms Under LOS/NLOS Mixture Conditions. IEEE Access 7 (2019)
Tae-Jun Park, Joon-Hyuk Chang
Dempster-Shafer theory for enhanced statistical model-based voice activity detection. Comput. Speech Lang. 47 (2018)
Moa Lee, Joon-Hyuk Chang
Augmenting Bottleneck Features of Deep Neural Network Employing Motor State for Speech Recognition at Humanoid Robots. CoRR (2018)
Moa Lee, Joon-Hyuk Chang
DNN-based Speech Recognition System dealing with Motor State as Auxiliary Information of DNN for Head Shaking Robot. IROS (2018)
Bong-Ki Lee, Kyoung Jin Noh, Joon-Hyuk Chang, Kihyun Choo, Eunmi Oh
Sequential Deep Neural Networks Ensemble for Speech Bandwidth Extension. IEEE Access 6 (2018)
Chee-Hyun Park, Joon-Hyuk Chang
Sequential source localisation and range estimation based on shrinkage algorithm. IET Signal Process. 12 (2) (2018)
Soojeong Lee, Sreeraman Rajan, Gwanggil Jeon, Joon-Hyuk Chang, Hilmi R. Dajani, Voicu Z. Groza
Oscillometric blood pressure estimation by combining nonparametric bootstrap with Gaussian mixture model. Comput. Biol. Medicine 85 (2017)
Soojeong Lee, Joon-Hyuk Chang
Spectral difference for statistical model-based speech enhancement in speech recognition. Multim. Tools Appl. 76 (23) (2017)
Soojeong Lee, Joon-Hyuk Chang
Oscillometric Blood Pressure Estimation Based on Deep Learning. IEEE Trans. Ind. Informatics 13 (2) (2017)
Soojeong Lee, Joon-Hyuk Chang
Deep Belief Networks Ensemble for Blood Pressure Estimation. IEEE Access 5 (2017)
Chee-Hyun Park, Joon-Hyuk Chang
TOA source localization and DOA estimation algorithms using prior distribution for calibrated source. Digit. Signal Process. 71 (2017)
Soojeong Lee, Joon-Hyuk Chang
Deep learning ensemble with asymptotic techniques for oscillometric blood pressure estimation. Comput. Methods Programs Biomed. 151 (2017)
Chee-Hyun Park, Joon-Hyuk Chang
Adaptive robust time-of-arrival source localization algorithm based on variable step size weighted block Newton method. EURASIP J. Wirel. Commun. Netw. 2017 (2017)
Ji-Won Cho, Jong-Hyeon Park, Joon-Hyuk Chang, Hyung-Min Park
Bayesian feature enhancement using independent vector analysis and reverberation parameter re-estimation for noisy reverberant speech recognition. Comput. Speech Lang. 46 (2017)
Ku-young Chung, Kwang-Sub Song, Kangsoo Shin, Jinho Sohn, Seok Hyun Cho, Joon-Hyuk Chang
Noncontact Sleep Study by Multi-Modal Sensor Fusion. Sensors 17 (7) (2017)
Soojeong Lee, Joon-Hyuk Chang
On using multivariate polynomial regression model with spectral difference for statistical model-based speech enhancement. J. Syst. Archit. 64 (2016)
Jee-Hye Lee, Myungin Lee, Joon-Hyuk Chang
Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech Recognition. CoRR (2016)
Chee-Hyun Park, Joon-Hyuk Chang
Time-of-arrival source localization based on weighted least squares estimator in line-of-sight/non-line-of-sight mixture environments. Int. J. Distributed Sens. Networks 12 (12) (2016)
Chee-Hyun Park, Joon-Hyuk Chang
Closed-Form Localization for Distributed MIMO Radar Systems Using Time Delay Measurements. IEEE Trans. Wirel. Commun. 15 (2) (2016)
Chee-Hyun Park, Joon-Hyuk Chang
Robust time-of-arrival source localization employing error covariance of sample mean and sample median in line-of-sight/non-line-of-sight mixture environments. EURASIP J. Adv. Signal Process. 2016 (2016)
Myungin Lee, Joon-Hyuk Chang
Blind estimation of reverberation time using deep neural network. IC-NIDC (2016)
Bong-Ki Lee, Joon-Hyuk Chang
Novel adaptive muting technique for packet loss concealment of ITU-T G.722 using optimized parametric shaping functions. EURASIP J. Audio Speech Music. Process. 2016 (2016)
Seng Hyun Huang, Jihwan Park, Joon-Hyuk Chang
Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probabilities. ICASSP (2016)
Inyoung Hwang, Hyung-Min Park, Joon-Hyuk Chang
Ensemble of deep neural networks using acoustic environment classification for statistical model-based voice activity detection. Comput. Speech Lang. 38 (2016)
Bong-Ki Lee, Joon-Hyuk Chang
Packet Loss Concealment Based on Deep Neural Networks for Digital Speech Transmission. IEEE ACM Trans. Audio Speech Lang. Process. 24 (2) (2016)
Ku-young Chung, Bong-Ki Lee, Kwang-Sub Song, Kangsoo Shin, Seok Hyun Cho, Joon-Hyuk Chang
An experimental study: The sufficient respiration rate detection technique via continuous wave Doppler radar. IC-NIDC (2016)

Joon-Hyuk Chang.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Joon-Hyuk Chang