Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Robert Leroy Mercer"'
Autor:
Stanley F. Chen, Robert Leroy Mercer, V. Della Pietra, Peter Fitzhugh Brown, Andrew Kehler, S. Della Pietra
Publikováno v:
Computer Speech & Language. 8:177-187
It has been observed that humans can translate nearly four times as quickly with little loss in accuracy simply by dictating, as opposed to typing, their translations. In this paper, we consider the integration of speech recognition into a translator
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4565659dff450ed169b3bc9eeba619d
https://doi.org/10.1006/csla.1994.1008
https://doi.org/10.1006/csla.1994.1008
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 5(2)
Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of statistical models for use in speech recognition. We g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dda0e7bf6c926ead02f6bdd984e2f172
https://pubmed.ncbi.nlm.nih.gov/21869099
https://pubmed.ncbi.nlm.nih.gov/21869099
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 1:443-452
A technique for constructing Markov models for the acoustic representation of words is described. Word models are constructed from models of subword units called fenones. Fenones represent very short speech events and are obtained automatically throu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0660a767e9bbd786d5f271259efc2a56
https://doi.org/10.1109/89.242490
https://doi.org/10.1109/89.242490
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 1:77-83
The problem of estimating the parameter values of hidden Markov word models for speech recognition is addressed. It is argued that maximum-likelihood estimation of the parameters via the forward-backward algorithm may not lead to values which maximiz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b65e8c4ddfad0827a4c40265363d2be
https://doi.org/10.1109/89.221369
https://doi.org/10.1109/89.221369
Publikováno v:
IEEE Transactions on Speech and Audio Processing. 1:59-67
In a large vocabulary speech recognition system using hidden Markov models, calculating the likelihood of an acoustic signal segment for all the words in the vocabulary involves a large amount of computation. In order to run in real time on a modest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e79fb653e8b4bb9fc148a284ef73b6d7
https://doi.org/10.1109/89.221368
https://doi.org/10.1109/89.221368
Publikováno v:
Information Processing & Management. 27:517-522
Some mistakes in spelling and typing produce correct words, such as typing “fig” when “fog” was intended. These errors are undetectable by traditional spelling correction techniques. In this paper we present a statistical technique capable of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::602d2b065d28439c8a7aa7ea93f69532
https://doi.org/10.1016/0306-4573(91)90066-u
https://doi.org/10.1016/0306-4573(91)90066-u
Autor:
Frederick Jelinek, J. Baker, A. Cole, Burn L. Lewis, Lalit R. Bahl, Robert Leroy Mercer, Paul S. Cohen
Publikováno v:
ICASSP
We report performance results on the recognition of continuously spoken sentences from the finite state grammar for the "New Raleigh Language" (vocabulary-250 words; average sentence length-8 words; entropy-2.86 bits/word; perplexity-7.27 words). Sen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fdc2b4028faf9d4bd97d9136c62fc975
https://doi.org/10.1109/icassp.1978.1170404
https://doi.org/10.1109/icassp.1978.1170404
Autor:
Burn L. Lewis, Lalit R. Bahl, Paul S. Cohen, Raimo Bakis, A. Cole, Frederick Jelinek, Robert Leroy Mercer
Publikováno v:
ICASSP
This paper describes the results of an experiment in which we have applied our speech recognition system to the problem of recognizing sentences from our restricted laser-patent corpus when the sentences are read with pauses between the words. Except
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d52f38da90643b202329c74f16e621b
https://doi.org/10.1109/icassp.1981.1171115
https://doi.org/10.1109/icassp.1981.1171115
Autor:
Lalit R. Bahl, A. Cole, A. Nadas, Paul S. Cohen, Raimo Bakis, Burn L. Lewis, Robert Leroy Mercer, Frederick Jelinek
Publikováno v:
ICASSP
Automatic selection of acoustic prototypes is an important step towards making speech recognition systems automatically adaptable to new speakers. Two methods for automatically obtaining a set of acoustic prototypes for use by a centisecond labeling
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe19a815398b92a93da4a98069165ae2
https://doi.org/10.1109/icassp.1981.1171177
https://doi.org/10.1109/icassp.1981.1171177
Autor:
Burn L. Lewis, J. Baker, Paul S. Cohen, Frederick Jelinek, Robert Leroy Mercer, Lalit R. Bahl
Publikováno v:
ICASSP
Preliminary results have been obtained with a system for recognizing continuously read sentences from a naturally-occurring corpus (Laser Patents), restricted to a 1000-word vocabulary. Our model of the task language has an entropy of about 4.8 bits/
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::934f10692c9c18ab3383ad5acd74963f
https://doi.org/10.1109/icassp.1978.1170402
https://doi.org/10.1109/icassp.1978.1170402