Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Wenhu Wu"'
Publikováno v:
2017 29th Chinese Control And Decision Conference (CCDC).
High starting current is one of the most important issues which restrict the development of Permanent-Magnet Synchronous Motor(PMSM) which could result in the serious damage of the insulation premature. In this work, a novel rotor configuration based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::313aa13acd00b8dbc066daf3652244b3
https://doi.org/10.1109/ccdc.2017.7978425
https://doi.org/10.1109/ccdc.2017.7978425
Publikováno v:
Speech Communication. 50:605-615
This paper discusses and evaluates a novel but simple and effective acoustic modeling method called ''state-dependent phoneme-based model merging (SDPBMM)'', used to build dialectal Chinese speech recognizer from a small amount of dialectal Chinese s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::71918ff61268c7319b15938e13079fa8
https://doi.org/10.1016/j.specom.2008.04.006
https://doi.org/10.1016/j.specom.2008.04.006
Publikováno v:
Speech Communication. 48:1273-1282
We propose a tree-based kernel selection (TBKS) algorithm as a computationally efficient approach to the Gaussian mixture model–universal background model (GMM–UBM) based speaker identification. All Gaussian components in the universal background
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e70a9117971069a491ab3e301d2f9ead
https://doi.org/10.1016/j.specom.2006.06.011
https://doi.org/10.1016/j.specom.2006.06.011
Publikováno v:
Journal of Electronics (China). 17:242-247
The co-articulation is one of the main reasons that makes the speech recognition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend on the first-order assumption. In this paper, for mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68c16f4d19c240365030453e6335e8ce
https://doi.org/10.1007/s11767-000-0037-5
https://doi.org/10.1007/s11767-000-0037-5
Publikováno v:
Journal of Computer Science and Technology. 14:18-26
In this paper, a novel technique adopted in HarkMan is introduced. HarkMan is a keyword-spotter designed to automatically spot the given words of a vocabulary-independent task in unconstrained Chinese telephone speech. The speaking manner and the num
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc4497985d61a34cd62f154244ba032a
https://doi.org/10.1007/bf02952483
https://doi.org/10.1007/bf02952483
Publikováno v:
Journal of Computer Science and Technology. 13:426-437
In this paper, a new statistic model named Center-Distance Continuous Probability Model (CDCPM) for speech recognition is described, which is based on Center-Distance Normal (CDN) distribution. In a CDCPM, the probability transition matrix is omitted
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de0e978584e70de9a87c907a5442ea5e
https://doi.org/10.1007/bf02948501
https://doi.org/10.1007/bf02948501
Publikováno v:
INTERSPEECH
To make full use of a small development data set to build a robust dialectal Chinese speech recognizer from a standard Chinese speech recognizer (based on Chinese Initial/Final, IF), a novel, simple but effective acoustic modeling method, named state
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31a565b50ebafc8552ad9f8a67dafca7
https://doi.org/10.21437/interspeech.2007-485
https://doi.org/10.21437/interspeech.2007-485
Publikováno v:
ICASSP (4)
In this paper, a session variability subspace projection (SVSP) based model compensation method for speaker verification is proposed. During the training phase the session variability is removed from speaker models by projection, while during the tes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::803b8369588d7666f8e45065f1e92310
https://doi.org/10.1109/icassp.2007.367162
https://doi.org/10.1109/icassp.2007.367162
Publikováno v:
ICASSP (1)
In this paper a new method of reducing the computational load for Gaussian mixture model universal background model (GMM-UBM) based speaker identification is proposed. In order to speed up the selection of N-best Gaussian mixtures in a UBM, a selecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::425546307456d89b731932f45ef48db0
https://doi.org/10.1109/icassp.2005.1415191
https://doi.org/10.1109/icassp.2005.1415191
Publikováno v:
Interspeech 2006.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ecc298545c56a84c86c6bf215b7f1409
https://doi.org/10.21437/interspeech.2006-36
https://doi.org/10.21437/interspeech.2006-36