Naoya Takahashi

data augmentation (2) convolutional neural network (2) audio source separation (2) voice conversion (2) automatic speech recognition (2) deep neural network (2) speech synthesis (1) deep learning (1) speech separation (1) low-resource learning (1) multimodal learning (1) speech enhancement (1) acoustic modeling (1) audio-visual correspondence (1) phoneme recognition (1) speech recognition (1) iterative learning (1) receptive field (1) style transfer (1) semi-supervised learning (1)