Skip to content
conftrace_

Kangwook Jang

7 papers · 2022–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird

Venues

Interspeech (5) ICLR (1) ICML (1)

Top co-authors

Hoirin Kim (4) Se-Young Yun (3) Sungnyun Kim (3) Sangmin Bae (2) Sungwoo Cho (2) Jahyun Goo (1) Yeonghyeon Lee (1) Youngmoon Jung (1) Hyun Myung Kim (1) Hyebin Ahn (1)

Research topics

Machine Learning (5) Speech & Audio (5) Deep Learning (4) Recognition (4) Application Areas (3) Architectures (3) Artificial Intelligence (1) Analysis (1) Core AI (1) Core Methods (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Synthesis (1)

Keywords

speech self-supervised learning (2) self-supervised learning (2) speaker verification (2) knowledge distillation (2) model compression (2) phoneme recognition (1) noise robustness (1) multimodal representation (1) attention map (1) audio deepfake detection (1) word error rate (1) audio-visual speech recognition (1) speech foundation model (1) robust speech recognition (1) hierarchical gating (1) cross-modal knowledge (1) one-class learning (1) sparse moe (1) variance invariance covariance regularization (1) noise extraction (1)

Papers

HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization Interspeech 2025 MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition ICML 2025 Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation ICLR 2025 ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction Interspeech 2025 One-class learning with adaptive centroid shift for audio deepfake detection Interspeech 2024 Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation Interspeech 2023 FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Models Interspeech 2022