← Authors

Kyogu Lee

15 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge πŸ† Grand Slam 🧬 Topic Evolution πŸ’Ž Century Club (15) πŸ—ƒοΈ Keyword Collector (66) πŸ”₯ Unstoppable (7)

Conferences

INTERSPEECH (7) ICLR (2) NIPS (2) AAAI (1) EMNLP (1) ICML (1) IJCAI (1)

Top co-authors

Eungbeom Kim (4) Hyeong-Seok Choi (4) Juheon Lee (3) Junghyun Koo (3) Jin Woo Lee (2) Yoori Oh (2) Jaehyun Park (2) Jaesung Huh (1) Min Jun Choi (1) Yoseob Han (1)

Keywords

automatic speech recognition (3) acoustic feature (2) semi-supervised learning (2) connectionist temporal classification (2) voice conversion (1) speech synthesis (1) domain adaptation (1) multimodal learning (1) self-supervised learning (1) emotion recognition (1) text analysis (1) adversarial training (1) spoofing detection (1) speech analysis (1) speaker verification (1) fundamental frequency (1) audio analysis (1) empirical risk minimization (1) video analysis (1) cross-domain learning (1)

Papers

Uncertainty-Aware Self-Training for CTC-Based Automatic Speech Recognition AAAI 2025
SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning IJCAI 2025
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion ICML 2025
Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation INTERSPEECH 2024
Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation NIPS 2024
Emosical: An Emotion-Annotated Musical Theatre Dataset EMNLP 2024
Hear Your Face: Face-based voice conversion with F0 estimation INTERSPEECH 2024
Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test INTERSPEECH 2023
Semi-supervised Learning for Continuous Emotional Intensity Controllable Speech Synthesis with Disentangled Representations INTERSPEECH 2023
Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification INTERSPEECH 2022
Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations NIPS 2021
From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech ICLR 2020
Exploiting Multi-Modal Features from Pre-Trained Networks for Alzheimer’s Dementia Recognition INTERSPEECH 2020
Adversarially Trained End-to-End Korean Singing Voice Synthesis System INTERSPEECH 2019
Phase-Aware Speech Enhancement with Deep Complex U-Net ICLR 2019