Zobrazeno 1 - 10
of 150
pro vyhledávání: '"Hirano, Masato"'
Autor:
Uhlich, Stefan, Fabbro, Giorgio, Hirano, Masato, Takahashi, Shusuke, Wichern, Gordon, Roux, Jonathan Le, Chakraborty, Dipam, Mohanty, Sharada, Li, Kai, Luo, Yi, Yu, Jianwei, Gu, Rongzhi, Solovyev, Roman, Stempkovskiy, Alexander, Habruseva, Tatiana, Sukhovei, Mikhail, Mitsufuji, Yuki
This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail
Externí odkaz:
http://arxiv.org/abs/2308.06981
Autor:
Shi, Hao, Shimada, Kazuki, Hirano, Masato, Shibuya, Takashi, Koyama, Yuichiro, Zhong, Zhi, Takahashi, Shusuke, Kawahara, Tatsuya, Mitsufuji, Yuki
Diffusion-based generative speech enhancement (SE) has recently received attention, but reverse diffusion remains time-consuming. One solution is to initialize the reverse diffusion process with enhanced features estimated by a predictive SE system.
Externí odkaz:
http://arxiv.org/abs/2305.10734
Autor:
Zhong, Zhi, Shi, Hao, Hirano, Masato, Shimada, Kazuki, Tateishi, Kazuya, Shibuya, Takashi, Takahashi, Shusuke, Mitsufuji, Yuki
Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in classification tasks.
Externí odkaz:
http://arxiv.org/abs/2305.06701
We have developed a diffusion-based speech refiner that improves the reference-free perceptual quality of the audio predicted by preceding single-channel speech separation models. Although modern deep neural network-based speech separation models hav
Externí odkaz:
http://arxiv.org/abs/2305.05857
Autor:
Zhong, Zhi, Hirano, Masato, Shimada, Kazuki, Tateishi, Kazuya, Takahashi, Shusuke, Mitsufuji, Yuki
Although music is typically multi-label, many works have studied hierarchical music tagging with simplified settings such as single-label data. Moreover, there lacks a framework to describe various joint training methods under the multi-label setting
Externí odkaz:
http://arxiv.org/abs/2302.08136
Publikováno v:
In Building and Environment 1 October 2024 264
Autor:
Hirano, Masato, Furuya, Shinichi
Publikováno v:
In iScience 19 January 2024 27(1)
Autor:
Choi, Narae, Yamanaka, Toshio, Takemura, Akihisa, Kobayashi, Tomohiro, Eto, Aya, Hirano, Masato
Publikováno v:
In Building and Environment September 2022 223
Autor:
Hirano, Masato1,2 (AUTHOR) hiraramasa@gmail.com, Furuya, Shinichi1,2 (AUTHOR)
Publikováno v:
Scientific Reports. 7/22/2022, Vol. 12 Issue 1, p1-12. 12p.
Publikováno v:
In Brain Stimulation November-December 2015 8(6):1195-1204