22 code implementations • 24 Oct 2017 • Hideyuki Tachibana, Katsuya Uenoyama, Shunsuke Aihara
This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units.
1 code implementation • 21 Sep 2020 • Hideyuki Tachibana, Yotaro Katayama
The authors applied this technique to an existing large vocabulary Japanese dictionary NEologd, and obtained a large vocabulary Japanese accent dictionary.
no code implementations • 22 Oct 2020 • Hideyuki Tachibana
In neural network-based monaural speech separation techniques, it has been recently common to evaluate the loss using the permutation invariant training (PIT) loss.
no code implementations • 26 Dec 2021 • Hideyuki Tachibana, Mocho Go, Muneyoshi Inahara, Yotaro Katayama, Yotaro Watanabe
Diffusion generative models have emerged as a new challenger to popular deep neural generative models such as GANs, but have the drawback that they often require a huge number of neural function evaluations (NFEs) during synthesis unless some sophisticated sampling strategies are employed.
no code implementations • 24 Aug 2022 • Mocho Go, Hideyuki Tachibana
Following the success in language domain, the self-attention mechanism (transformer) is adopted in the vision domain and achieving great success recently.
Ranked #42 on Instance Segmentation on COCO test-dev
no code implementations • 26 Mar 2024 • Chihiro Yano, Akihiko Fukuchi, Shoko Fukasawa, Hideyuki Tachibana, Yotaro Watanabe
Prior work on multilingual sentence embedding has demonstrated that the efficient use of natural language inference (NLI) data to build high-performance models can outperform conventional methods.