Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Shirin Saleem"'
Autor:
David Stallard, Prem Natarajan, Jacob Devlin, Mark Rawls, Chia-Lin Kao, Shankar Ananthakrishnan, Kriste Krstovski, Aaron Challenner, Fred Choi, Stavros Tsakalidis, Rohit Prasad, Ralf Meermeier, Shirin Saleem
Publikováno v:
Computer Speech & Language. 27:475-491
In this paper we present a speech-to-speech (S2S) translation system called the BBN TransTalk that enables two-way communication between speakers of English and speakers who do not understand or speak English. The BBN TransTalk has been configured fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41014688a94724ba064cc8106ba566c5
https://doi.org/10.1016/j.csl.2011.10.003
https://doi.org/10.1016/j.csl.2011.10.003
Publikováno v:
International Journal of Document Analysis and Recognition (IJDAR). 10:187-198
This paper addresses two types of classification of noisy, unstructured text such as newsgroup messages: (1) spotting messages containing topics of interest, and (2) automatic conceptual organization of messages without prior knowledge of topics of i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::018decc0cf307870340d499b4f9e794e
https://doi.org/10.1007/s10032-007-0057-x
https://doi.org/10.1007/s10032-007-0057-x
Autor:
Rohit Prasad, Shiv Vitaladevuni, Premkumar Natarajan, David Belanger, Huaigu Cao, Krishna Subramanian, Matin Kamali, Ehry MacRostie, Shirin Saleem
Publikováno v:
Guide to OCR for Arabic Scripts ISBN: 9781447140719
We describe BBN’s script-independent methodology for multilingual machine-print OCR and offline handwriting recognition (HWR) based on the use of hidden Markov models (HMM). The feature extraction, training, and recognition components of the system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47d187af4ce2e817ba796c9b2321cf9f
https://doi.org/10.1007/978-1-4471-4072-6_20
https://doi.org/10.1007/978-1-4471-4072-6_20
Autor:
Shirin Saleem, Yue Wu, Ehry MacRostie, Pradeep Natarajan, Rohit Prasad, Fred Bernardin, Prem Natarajan
Publikováno v:
ICME
Robust, real-time, multi-class logo detection in high resolution broadcast videos presents several difficult challenges. For most logos we only have a few training samples, which makes training robust classifiers hard. Also, logos could potentially o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b492f854623c1cd581a4cd8d96ab1f8
https://doi.org/10.1109/icme.2011.6012121
https://doi.org/10.1109/icme.2011.6012121
Autor:
Kriste Krstovski, Prem Natarajan, David Stallard, Rohit Prasad, Shirin Saleem, Shankar Ananthakrishnan, Ralf Meermeier, Jacob Devlin, Fred Choi
Publikováno v:
Speech and Language Technologies
Portable translation devices which enable people who speak different languages to communicate with each another in voice are likely to have a far-reaching impact in both the civilian and military worlds. While long a staple of science fiction, a la t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2fc6aecdcc5f5457004e1391e6fbebc5
https://doi.org/10.5772/19405
https://doi.org/10.5772/19405
Autor:
Rohit Prasad, David Stallard, Fred Choi, Shankar Ananthakrishnan, Shirin Saleem, Prem Natarajan
Publikováno v:
ICASSP
Speech-to-speech translation systems have made a great deal of progress in recent years. But users of such systems still face the problem of not knowing whether the system has translated their utterance correctly. Various confirmation strategies can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8991f5c31aa5e7a7e4df95e7a3fa9e11
https://doi.org/10.1109/icassp.2010.5495000
https://doi.org/10.1109/icassp.2010.5495000
Publikováno v:
Interspeech 2009.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a23a229092a6099379d8df196c7ca8c9
https://doi.org/10.21437/interspeech.2009-155
https://doi.org/10.21437/interspeech.2009-155
Publikováno v:
ICDAR
Offline handwriting recognition of free-flowing Arabic text is a challenging task due to the plethora of factors that contribute to the variability in the data. In this paper, we address some of these sources of variability, and present experimental
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0c18f9a42771811843a3a1692b1e308
https://doi.org/10.1109/icdar.2009.282
https://doi.org/10.1109/icdar.2009.282
Publikováno v:
ICDAR
In this paper we present an innovative two-stage adaptation approach for handwriting recognition that is based on clustering of similar pages in the training data. In our approach, we first perform page clustering on training data using features such
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d935a1a4f98f68031713ebf83a831e79
https://doi.org/10.1109/icdar.2009.77
https://doi.org/10.1109/icdar.2009.77
Autor:
Pradeep Natarajan, Chia-Lin Kao, Shirin Saleem, Stavros Tsakalidis, Rohit Prasad, David Stallard, Ralf Meermeier, Fred Choi, Krishna Subramanian, Kriste Krstovski, C. Corbett Moran
Publikováno v:
SLT
We report on recent improvements in our English/Iraqi Arabic speech-to-speech translation system. User interface improvements include a novel parallel approach to user confirmation which makes confirmation cost-free in terms of dialog duration. Autom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a52ad3c717a6d4bf170dff856a1ce12
https://doi.org/10.1109/slt.2008.4777886
https://doi.org/10.1109/slt.2008.4777886