Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Scott Shaobing Chen"'
Autor:
Scott Shaobing Chen1 schen@watson.ibm.com, Donoho, David L.2 donoho@stat.stanford.edu, Saunders, Michael A.3 mike@SOL-Michael.stanford.edu
Publikováno v:
SIAM Journal on Scientific Computing. 1998, Vol. 20 Issue 1, p33-61. 29p.
Autor:
D. Kanvesky, M. J. F. Gales, Ellen Eide, Scott Shaobing Chen, Ramesh A. Gopinath, Peder A. Olsen
Publikováno v:
Speech Communication. 37:69-87
This paper describes the IBM approach to Broadcast News (BN) transcription. Typical problems in the BN transcription task are segmentation, clustering, acoustic modeling, language modeling and acoustic model adaptation. This paper presents new algori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b43abb5a16e34039df0a1fae462d470
https://doi.org/10.1016/s0167-6393(01)00060-7
https://doi.org/10.1016/s0167-6393(01)00060-7
Autor:
Scott Shaobing Chen, D.L. Donoho
Publikováno v:
ICASSP
We apply basis pursuit, an atomic decomposition technique, for spectrum estimation. Compared with several modern time series methods, our approach can greatly reduce the problem of power leakage; it is able to superresolve; moreover, it works well wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24eeeca392ca3a3b6f92f42c95a1403d
https://doi.org/10.1109/icassp.1998.681827
https://doi.org/10.1109/icassp.1998.681827
Publikováno v:
ICASSP
One difficult problem we are often faced with in clustering analysis is how to choose the number of clusters. We propose to choose the number of clusters by optimizing the Bayesian information criterion (BIC), a model selection criterion in the stati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a52940b7aac2b2aa1f604ab656c2dc7
https://doi.org/10.1109/icassp.1998.675347
https://doi.org/10.1109/icassp.1998.675347
Autor:
Ramesh A. Gopinath, Ponani S. Gopalakrishnan, Scott Shaobing Chen, Raimo Bakis, L. Polymenalos, Stephane H. Maes
Publikováno v:
ICASSP
This paper describes some of the main problems and issues specific to the transcription of broadcast news and describes some of the methods for solving them that have been incorporated into the IBM Large Vocabulary Continuous Speech Recognition Syste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c5d38aa08efca531959b252e45aa7a1
https://doi.org/10.1109/icassp.1997.596001
https://doi.org/10.1109/icassp.1997.596001
Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news
Autor:
Dimitri Kanevsky, Mark J. F. Gales, Ellen Eide, Scott Shaobing Chen, Peder A. Olsen, Ramesh A. Gopinath
Publikováno v:
ICASSP
We describe extensions and improvements to IBM's system for automatic transcription of broadcast news. The speech recognizer uses a total of 160 hours of acoustic training data, 80 hours more than for the system described in Chen et al. (1998). In ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86353bccbf2d40c11ef9d6ce127943e6
https://doi.org/10.1109/icassp.1999.758056
https://doi.org/10.1109/icassp.1999.758056
Autor:
Scott Shaobing Chen, Peter DeSouza
Publikováno v:
5th European Conference on Speech Communication and Technology (Eurospeech 1997).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ca38ede669ce1b3c74cea1b461f297a
https://doi.org/10.21437/eurospeech.1997-558
https://doi.org/10.21437/eurospeech.1997-558
Publikováno v:
Proceedings of the 1998 IEEE International Conference on Acoustics, Speech & Signal Processing, ICASSP '98 (Cat No98CH36181); 1998, Issue 2, p645-645, 1p