180 citations
- NAVER Cloud (South Korea)KR39 papers
- Korea Advanced Institute of Science and TechnologyKR12 papers
- Sungkyunkwan UniversityKR9 papers
- Seoul National UniversityKR8 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 cs.SDShow all
3 papers · 1 filter
cs.SD2023
Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech
Hyungchan Yoon, Changhwan Kim, Eunwoo Song +2
For personalized speech generation, a neural text-to-speech (TTS) model must be successfully implemented with limited data from a target speaker. To this end, the baseline TTS mode…
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.…