Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Paul G. Bamberg"'
Autor:
Paul G. Bamberg
Publikováno v:
Applied Mathematics. :550-561
“Consanguinity” is a gender-neutral term for “fraternity” or “sorority.” Initially a consanguinity includes M male members and F female members. Each week a member, chosen at random, selects a new member, always of the same gender as the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::776e3b31b0b42801331fd683ea098954
https://doi.org/10.4236/am.2017.84044
https://doi.org/10.4236/am.2017.84044
Autor:
Paul G. Bamberg, Mark A. Mandel
Publikováno v:
Speech Communication. 10:437-451
For a large-vocabulary speech-recognition system, such as Dragon Systems' 30,000 word DragonDictate recognizer, an efficient approach to training is to use “phonemes-in-context” (PICs) which are triphones supplemented by a code to describe prepau
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::209087a76c905949ec7db24c53694e3e
https://doi.org/10.1016/0167-6393(91)90047-w
https://doi.org/10.1016/0167-6393(91)90047-w
Autor:
Paul G. Bamberg, Linda Manganaro, Haakon L. Chevalier, Taiko Dietzel, Jonathan Yamron, Todd P. Margolis, Frank Kampmann, James K. Baker, John Elder, Mark Mandel, Elizabeth E. Steele
Publikováno v:
HLT
In this paper we present the first implementation of LINGSTAT, an interactive machine translation system designed to increase the productivity of a user, with little knowledge of the source language, in translating or extracting information from fore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0125a5b8dbafbc427aae868b2e5029ce
https://doi.org/10.3115/1075671.1075714
https://doi.org/10.3115/1075671.1075714
Autor:
Stephen Lowe, Kathleen Bishop, Paul G. Bamberg, Zezhen Huang, Janet M. Baker, Francesco Scattone, Yoshiko Ito, James K. Baker, Vera Helman, Larry Gillick, Robert Roth, Barbara Peskin
Publikováno v:
HLT
In this paper we present some of the algorithm improvements that have been made to Dragon's continuous speech recognition and training programs, improvements that have more than halved our error rate on the Resource Management task since the last SLS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75a9b800a94d6c5b56b635e8fef5c3da
https://doi.org/10.3115/1075527.1075621
https://doi.org/10.3115/1075527.1075621
Autor:
Lori Lamel, Ousmane Ba, Janet M. Baker, Richard Benedict, Dean Sturtevant, James K. Baker, Francesco Scattone, Robert Roth, Larry Gillick, Paul G. Bamberg
Publikováno v:
HLT
In this paper we present preliminary results obtained at Dragon Systems on the Resource Management benchmark task. The basic conceptual units of our system are Phonemes-in-Context (PICs), which are represented as Hidden Markov Models, each of which i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::562c5264cb843f4ab8cadbfc4e45987b
https://doi.org/10.3115/112405.112412
https://doi.org/10.3115/112405.112412
Autor:
Laurence S. Gillick, Paul G. Bamberg
Publikováno v:
HLT
For large-vocabulary continuous speech recognition, the goal of training is to model phonemes with enough precision so that from the models one could reconstruct a sequence of acoustic parameters that accurately represents the spectral characteristic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ceffe9e71a3cc2b465af2aa40ba9e103
https://doi.org/10.3115/116580.116635
https://doi.org/10.3115/116580.116635
Publikováno v:
HLT
We present a 1000-word continuous speech recognition (CSR) system that operates in real time on a personal computer (PC). The system, designed for large vocabulary natural language tasks, makes use of phonetic Hidden Markov models (HMM) and incorpora
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c75a8d596928a55eaf23e876cb17394
https://doi.org/10.3115/116580.116610
https://doi.org/10.3115/116580.116610
Autor:
Eric Fieleke, Joel M. Gould, Kenneth J. Bayse, Roger L. Matus, Michael L. Elkins, Charles E. Ingold, Paul G. Bamberg
Publikováno v:
The Journal of the Acoustical Society of America. 118:1259
A computer is used to perform recorded actions. The computer receives recorded spoken utterances of actions. The computer then performs speech recognition on the recorded spoken utterances to generate texts of the actions. The computer then parses th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f88d8c9a7766f41691eef84a5e51750
https://doi.org/10.1121/1.2097109
https://doi.org/10.1121/1.2097109
Autor:
Paul G. Bamberg, Jed M. Roberts, Caroline B. Huang, Claudia L. E. Ellermann, James K. Baker, Stijn Vaeven
Publikováno v:
The Journal of the Acoustical Society of America. 105:27
A system and associated methods for recognizing (12) compound words from an utterance (22) containing a succession of one or more words from a predetermined vocabulary. At least one of the words in the utterance is a compound word including at least
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d618fb2c2435dc7ecd2aea5a14f116f
https://doi.org/10.1121/1.424703
https://doi.org/10.1121/1.424703
Publikováno v:
The Journal of the Acoustical Society of America. 90:2881-2881
A first speech recognition method receives an acoustic description of an utterance to be recognized and scores a portion of that description against each of a plurality of cluster models representing similar sounds from different words. The resulting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6a563ae7ae2f03d197a2ce4e313b48e
https://doi.org/10.1121/1.402379
https://doi.org/10.1121/1.402379