구성원
- HOME
- 구성원
- 전임교원
전임교원
이상훈Sang-Hoon Lee
전공 : 소프트웨어학과
학위 : 박사
이메일 : sanghoonlee@ajou.ac.kr
연구실 : 팔달관 1004호
연구실번호 : 3811
연구실관심분야 : Deep learning, Speech AI
학력
- 2023.02 고려대학교 박사
경력
- 2024~현재: 아주대학교
- 2023~2024: 고려대학교 인공지능연구센터
연구분야
- Speech AI
연구활동(주요논문)
- [논문] H.-Y. Choi*, S.-H. Lee*, and S.-W. Lee, “DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixupfor Verified Robust Voice Conversion,”AAAI, 2024.
- [논문] S.-H. Lee, S.-B. Kim, J.-H. Lee, E. Song, M.-J. Hwang, and S.-W. Lee, “HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis,” Proc. of NeurIPS, 2022.
- [논문] S.-H. Lee H.-R. Noh, W. Nam, and S.-W. Lee, “Duration Controllable Voice Conversion via Phoneme-based Information Bottleneck,” IEEE/ACM Trans. on Audio, Speech, and,Language Processing. Vol.30. 2022.
- [논문] S.-H. Lee, J.-H. Kim, H. Chung, and S.-W. Lee, “VoiceMixer: Adversarial Voice Style Mixup,” Proc. of NeurIPS, 2021.
- [논문] [S.-H. Lee H.-W. Yoon, H.-R. Noh, J.-H. Kim, and S.-W. Lee, “Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis,” Proc. of AAAI, 2021.
특허 및 기타
- "METHOD AND SYSTEM FOR SYNTHESIZING SPEECH," 10-2663162, 29, Apr., 2024.
- "METHOD TO TRANSFORM VOICE,", 10-2439022, 29, Aug., 2022.
- "METHOD AND APPARTUS FOR VOICE CONVERSION BY USING NEURAL NETWORK," 10-2340486, 14, Dec., 2021.
- "SYSTEM AND METHOD FOR CURLING SWEEPING CONTROL," 10-2257358, 21, May, 2021.
- "APPARATUS AND METHOD FOR RECOMMENDATION OF CURLING GAME STRATEGY USING DEEP LEARNING," 10-2045567, 11, Nov., 2019.
- "APPARATUS AND METHOD FOR DELIVERY AND SWEEPING AT CURLING GAME," 10-1948713, 11, Feb., 2019.
- 입학
- 커뮤니티
- 대학원 공지사항
- 학과 공지사항
- 세미나
- Publication
우) 16499 경기도 수원시 영통구 월드컵로 206 아주대학교 인공지능학과
Copyright 2021 Department of Artificial Intelligence. All Rights Reserved.