128 citations
- KDDI Research (Japan)JP2 papers
- Beihang UniversityCN1 paper
- California Institute of TechnologyUS1 paper
- Cambridge Quantum Computing (United Kingdom)GB1 paper
- Centrum Wiskunde & InformaticaNL1 paper
- Chinese University of Hong KongHK1 paper
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- ETH ZurichCH1 paper
- Fraunhofer-GesellschaftDE1 paper
- Fraunhofer Institute for Telecommunications, Heinrich Hertz InstituteDE1 paper
- Munich Center for Quantum Science and TechnologyDE1 paper
Showing 2019Show all
2 papers · 1 filter
eess.AS2019★ 3 cited
Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi +1
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers…
cs.LG2019★ 25 cited
Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis
Danilo Vasconcellos Vargas, Jiawei Su
Deep neural networks were shown to be vulnerable to single pixel modifications. However, the reason behind such phenomena has never been elucidated. Here, we propose Propagation Ma…