Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Tsuyoki Nishikawa"'
Autor:
Tsuyoki Nishikawa, Tomokazu Ishikawa
Publikováno v:
The Journal of The Institute of Image Information and Television Engineers. 70:886-890
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f74c737a56e7f5575048912a5fca74b
https://doi.org/10.3169/itej.70.886
https://doi.org/10.3169/itej.70.886
Publikováno v:
GCCE
Recently, many tourists visit Japan from various countries. Hence, automatic speech translation device is desired for services in various business scenes at a shopping, a station, a town, and a hotel. For realizing speech translation with higher accu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47d7107e6a0e6c1465d4709419810d34
https://doi.org/10.1109/gcce.2017.8229375
https://doi.org/10.1109/gcce.2017.8229375
Publikováno v:
GCCE
Voice applications often require the ability to make user-friendly responses by judging the user or user-type from an extremely short utterance, such as a single word. However, it is assumed that performance becomes degraded as the utterance length d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::83e43a14ad99578b2092ac254367c82c
https://doi.org/10.1109/gcce.2017.8229389
https://doi.org/10.1109/gcce.2017.8229389
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 14:666-678
We propose a new algorithm for blind source separation (BSS), in which independent component analysis (ICA) and beamforming are combined to resolve the slow-convergence problem through optimization in ICA. The proposed method consists of the followin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::572b470a9424244b0e30a16d8ab5c1eb
https://doi.org/10.1109/tsa.2005.855832
https://doi.org/10.1109/tsa.2005.855832
Publikováno v:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. (12):3593-3603
We propose utilizing subband-based blind source separation (BSS) for convolutive mixtures of speech. This is motivated by the drawback of frequency-domain BSS, i.e., when a long frame with a fixed long frame-shift is used to cover reverberation, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffd9093d91bc2dd60712716c91b11ead
http://hdl.handle.net/10061/7810
http://hdl.handle.net/10061/7810
Publikováno v:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. (9):2387-2400
We propose a new two-stage blind separation and deconvolution strategy for multiple-input multiple-output (MIMO)-FIR systems driven by colored sound sources, in which single-input multiple-output (SIMO)-model-based ICA (SIMO-ICA) and blind multichann
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df32e2a55fb5c9e9ca20b9fd11273678
http://hdl.handle.net/10061/7808
http://hdl.handle.net/10061/7808
Publikováno v:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. (7):1673-1682
In this paper, we address the blind separation problem of binaural mixed signals, and we propose a novel blind separation method, in which a self-generator for initial filters of Single-Input-Multiple-Output-model-based independent component analysis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71c7277b1acc6e9a9d5dad7e6641af87
http://hdl.handle.net/10061/7805
http://hdl.handle.net/10061/7805
Publikováno v:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. (8):2063-2072
We newly propose a novel blind separation framework for Single-Input Multiple-Output (SIMO) -model-based acoustic signals using an extended ICA algorithm, SIMO-ICA. The SIMO-ICA consists of multiple ICAs and a fidelity controller, and each ICA runs i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::670376b12f013dac14b8575815aadc42
http://hdl.handle.net/10061/7799
http://hdl.handle.net/10061/7799
Publikováno v:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. (8):1924-1932
We propose a new algorithm for overdetermined blind source separation (BSS) based on multistage independent component analysis (MSICA). To improve the separation performance, we have proposed MSICA in which frequency-domain ICA and time-domain ICA ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0a9fee2634c9ef59a5f502b811ad15f3
http://hdl.handle.net/10061/7798
http://hdl.handle.net/10061/7798
Autor:
Kazuya Takeda, Satoshi Kurita, Hiroshi Saruwatari, Kiyohiro Shikano, Fumitada Itakura, Tsuyoki Nishikawa
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2003, Iss 11, p 569270 (2003)
EURASIP Journal on Advances in Signal Processing, Vol 2003, Iss 11, Pp 1135-1146 (2003)
EURASIP Journal on Advances in Signal Processing, Vol 2003, Iss 11, Pp 1135-1146 (2003)
We describe a new method of blind source separation (BSS) on a microphone array combining subband independent component analysis (ICA) and beamforming. The proposed array system consists of the following three sections: (1) subband ICA-based BSS sect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8634556df988e6d4b2bd328e4f0b9bde
http://hdl.handle.net/10061/7785
http://hdl.handle.net/10061/7785