788 citations
- NTT (Japan)JP3 papers
- Kyoto UniversityJP2 papers
- Nagoya UniversityJP2 papers
- Aalto UniversityFI1 paper
- Academia SinicaTW1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- EURECOMFR1 paper
- Google (United States)US1 paper
- Hoya (Japan)JP1 paper
- IFlyTek (China)1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
- Johns Hopkins UniversityUS1 paper
3 papers
eess.AS2019★ 11 cited
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang, Junichi Yamagishi, Massimiliano Todisco +37
Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is v…
cs.CL2019★ 788 cited
A Comparative Study on Transformer vs RNN in Speech Applications
Shigeki Karita, Nanxin Chen, Tomoki Hayashi +10
Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS…
stat.ML2019
Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara +2
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, rece…