180 citations
- NAVER Cloud (South Korea)KR41 papers
- Korea Advanced Institute of Science and TechnologyKR15 papers
- Seoul National UniversityKR10 papers
- Sungkyunkwan UniversityKR10 papers
- Yonsei UniversityKR8 papers
- Virginia TechUS5 papers
- Line Corporation (Japan)JP4 papers
- University of TorontoCA4 papers
- Inha UniversityKR3 papers
- Kootenay Association for Science & TechnologyCA3 papers
- Korea UniversityKR3 papers
- Daegu Gyeongbuk Institute of Science and TechnologyKR2 papers
Showing 2019 · cs.SDShow all
2 papers · 2 filters
cs.SD2019★ 2 cited
The sound of my voice: speaker representation loss for target voice separation
Seongkyu Mun, Soyeon Choe, Jaesung Huh +1
Content and style representations have been widely studied in the field of style transfer. In this paper, we propose a new loss function using speaker content representation for au…
cs.SD2019★ 79 cited
Phase-aware Speech Enhancement with Deep Complex U-Net
Hyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh +3
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction.…