Kwanghee Choi
14 papers · 2021–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(8)
👥
Mega-Team
(76)
💎
Century Club
(12)
🗃️
Keyword Collector
(54)
🔥
Unstoppable
(5)
Conferences
INTERSPEECH (5)
ACL (3)
CVPR (1)
ECCV (1)
ICCV (1)
ICLR (1)
NAACL (1)
UAI (1)
Top co-authors
Keywords
self-supervised learning
(2)
speech recognition
(2)
foundation model
(2)
automatic speech recognition
(2)
phone recognition
(2)
uncertainty quantification
(1)
domain generalization
(1)
contrastive learning
(1)
semantic analysis
(1)
gaussian mixture model
(1)
model architecture
(1)
zero-shot learning
(1)
neural network optimization
(1)
phonetic analysis
(1)
knowledge distillation
(1)
label shift
(1)
mutual information
(1)
low-resource language
(1)
stochastic gradient descent
(1)
active learning
(1)
Papers
PRiSM: Benchmarking Phone Realization in Speech Models
ACL 2026
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
ACL 2026
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
ICLR 2025
Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment
NAACL 2025
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
INTERSPEECH 2024
Wav2Gloss: Generating Interlinear Glossed Text from Speech
ACL 2024
On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
INTERSPEECH 2024
Self-Supervised Speech Representations are More Phonetic than Semantic
INTERSPEECH 2024
TiDAL: Learning Training Dynamics for Active Learning
ICCV 2023
Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
INTERSPEECH 2023
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
ECCV 2022
Distilling a Pretrained Language Model to a Multilingual ASR Model
INTERSPEECH 2022
Combating the instability of mutual information-based losses via regularization
UAI 2022
Disentangling Label Distribution for Long-Tailed Visual Recognition
CVPR 2021