Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Masahito Togami"'
Autor:
Masahito TOGAMI
Publikováno v:
IEICE ESS Fundamentals Review. 16:257-271
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b549577daf2c666300e8861db126185f
https://doi.org/10.1587/essfr.16.4_257
https://doi.org/10.1587/essfr.16.4_257
Publikováno v:
IEEE Signal Processing Letters. 29:927-931
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::396dc340df54c966f7939e9a937526aa
https://doi.org/10.1109/lsp.2021.3134939
https://doi.org/10.1109/lsp.2021.3134939
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca0750f200caa3e5a2468001f88caba0
https://doi.org/10.21437/interspeech.2021-523
https://doi.org/10.21437/interspeech.2021-523
Autor:
Robin Scheibler, Masahito Togami
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d74c5accc56dd59568a650ee224a99a9
https://doi.org/10.21437/interspeech.2021-126
https://doi.org/10.21437/interspeech.2021-126
Publikováno v:
2021 29th European Signal Processing Conference (EUSIPCO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46a047c58765394801af7ad0cc0b0531
https://doi.org/10.23919/eusipco54536.2021.9616356
https://doi.org/10.23919/eusipco54536.2021.9616356
Autor:
Masahito Togami
Publikováno v:
ICASSP
In this paper, we propose a dereverberation and speech source separation method based on deep neural network (DNN). Unlike the cascade connection of dereverberation and speech source separation, the proposed method performs dereverberation and speech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0cdcb96f0b546b9c694c939c5f80d9ea
https://doi.org/10.1109/icassp39728.2021.9414907
https://doi.org/10.1109/icassp39728.2021.9414907
Publikováno v:
Human Robot Interaction
Automatic Speech Recognition (ASR) is an essential function of robots which live in the human world. Many works for ASR have been done for a long time. As a result, computers can recognize human speech well under silent environments. However, accurac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d60bcc9540ca4f861a939b171798cbc9
http://www.intechopen.com/articles/show/title/automatic_speech_recognition_of_human-symbiotic_robot_emiew
http://www.intechopen.com/articles/show/title/automatic_speech_recognition_of_human-symbiotic_robot_emiew
Publikováno v:
ICASSP
We propose a new algorithm for joint dereverberation and blind source separation (DR-BSS). Our work builds upon the IRLMA-T framework that applies a unified filter combining dereverberation and separation. One drawback of this framework is that it re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2975912b1b04331982b2d91946f79470
http://arxiv.org/abs/2102.06322
http://arxiv.org/abs/2102.06322
Autor:
Masahito Togami
Publikováno v:
EUSIPCO
In this paper, we propose a multi-channel speech source separation technique which connects an unsupervised spatial filtering without a deep neural network (DNN) to a DNN-based speech source separation in a cascade manner. In the speech source separa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4108d91052eb2a00587950e7643f072d
https://doi.org/10.23919/eusipco47968.2020.9287810
https://doi.org/10.23919/eusipco47968.2020.9287810
Publikováno v:
EUSIPCO
This paper proposes robust acoustic scene classification (ASC) to multiple devices using maximum classifier discrepancy (MCD) and knowledge distillation (KD). The proposed method employs domain adaptation to train multiple ASC models dedicated to eac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7f6e35250254310c00bbb2508ccaa5b
https://doi.org/10.23919/eusipco47968.2020.9287734
https://doi.org/10.23919/eusipco47968.2020.9287734