Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Ryo AIHARA"'
Publikováno v:
IEEE Access, Vol 12, Pp 36990-36999 (2024)
In this paper, we investigate the use of the spontaneous speech of dysarthric people for training an automatic speech recognition (ASR) model for them. Although the spontaneous speech of dysarthric people can be collected relatively easily compared t
Externí odkaz:
https://doaj.org/article/51e225758a6e43888c296ceb14e6dc71
Autor:
Yuki Takashima, Ryoichi Takashima, Ryota Tsunoda, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki, Nobuaki Motoyama
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-9 (2021)
Abstract We present an unsupervised domain adaptation (UDA) method for a lip-reading model that is an image-based speech recognition model. Most of conventional UDA methods cannot be applied when the adaptation data consists of an unknown class, such
Externí odkaz:
https://doaj.org/article/22667a463fb5441488e5b523b7cff10b
Publikováno v:
Journal of Advanced Mechanical Design, Systems, and Manufacturing, Vol 10, Iss 5, Pp JAMDSM0080-JAMDSM0080 (2016)
This paper presents a design study of an optical configuration for the fabrication of a two-dimensional grating, which will be used as a scale in a planar encoder system. For the modified two-axis Lloyd's mirror interferometer, in which major modific
Externí odkaz:
https://doaj.org/article/aec40025501b4f208312861332271c06
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8a4e9ccb13204a20236e29a432452d9
https://doi.org/10.1109/icassp43922.2022.9747204
https://doi.org/10.1109/icassp43922.2022.9747204
Publikováno v:
Acoustical Science and Technology. 41:465-471
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c2b03fcaf5826a7f9d268b0f95ee751
https://doi.org/10.1250/ast.41.465
https://doi.org/10.1250/ast.41.465
Publikováno v:
Precision Engineering. 52:138-151
A compact and stable two-axis Lloyd’s mirror interferometer based on a new non-orthogonal type of mirror-substrate assembly is designed for fabrication of 100 mm × 100 mm large-area two-dimensional (2D) diffraction scale gratings in a research lab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eddc0fb12fe07ff40d550be6f8da7241
https://doi.org/10.1016/j.precisioneng.2017.12.004
https://doi.org/10.1016/j.precisioneng.2017.12.004
Publikováno v:
ICASSP
The recently-proposed deep clustering algorithm introduced significant advances in monaural speaker-independent multi-speaker speech separation. Deep clustering operates on magnitude spectro-grams using bidirectional recurrent networks and K-means cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb351a9579fb30690f2942263b384b9e
https://doi.org/10.1109/icassp.2019.8682695
https://doi.org/10.1109/icassp.2019.8682695
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 24:1175-1184
A novel voice conversion (VC) method for arbitrary speakers is proposed. Non-negative matrix factorization (NMF) has recently been applied to exemplar-based VC. It offers noise robustness and naturalness of the converted voice, compared with widely u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd80bbde2db42d8246529e88cd394d1d
https://doi.org/10.1109/taslp.2016.2522643
https://doi.org/10.1109/taslp.2016.2522643
Autor:
Shingo Uenohara, Toshiyuki Hanazawa, Takanobu Uramoto, Taiki Izumi, Ken'ichi Furuya, Ryo Aihara, Yohei Okato
Publikováno v:
APSIPA
In this study, we propose efficient the number of computational iteration method of MNMF for speech recognition. The proposed method initializes and estimates the MNMF algorithm with respect to the estimated spatial correlation matrix reducing the nu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbd10b0c18a90d083b3a3061460a5d80
https://doi.org/10.23919/apsipa.2018.8659493
https://doi.org/10.23919/apsipa.2018.8659493
Autor:
Ken'ichi Furuya, Toshiyuki Hanazawa, Takanobu Uramoto, Yohei Okato, Taiki Izumi, Shingo Uenohara, Ryo Aihara
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319936581
CISIS
CISIS
In this paper, we propose efficient the number of computational iteration method of MNMF for speech recognition. The proposed method initializes estimates MNMF algorithm with the estimated spatial correlation matrix reduces the number of iteration of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c761131cf88eafb0d45f3aa2a40c7390
https://doi.org/10.1007/978-3-319-93659-8_82
https://doi.org/10.1007/978-3-319-93659-8_82
