Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Larry Gillick"'
Publikováno v:
Digital Signal Processing. 10:75-92
Weber, Frederick, Peskin, Barbara, Newman, Michael, Corrada-Emmanuel, Andres, and Gillick, Larry, Speaker Recognition on Single- and Multispeaker Data, Digital Signal Processing10(2000), 75?92.We discuss Dragon Systems' approach to the NIST Speaker R
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb5a429423e7c3598fe620bc7d5015e7
https://doi.org/10.1006/dspr.1999.0362
https://doi.org/10.1006/dspr.1999.0362
Publikováno v:
ICASSP
The parameters of the standard Hidden Markov Model framework for speech recognition are typically trained via Maximum Likelihood. However, better recognition performance is achievable with discriminative training criteria like Maximum Mutual Informat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82e57d0604df749f328d114348c0e59a
https://doi.org/10.1109/icassp.2012.6288979
https://doi.org/10.1109/icassp.2012.6288979
Publikováno v:
ASRU
We describe a series of experiments simulating data from the standard Hidden Markov Model (HMM) framework used for speech recognition. Starting with a set of test transcriptions, we begin by simulating every step of the generative process. In each su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d729270f227a18838411e109590aa6c
https://doi.org/10.1109/asru.2011.6163908
https://doi.org/10.1109/asru.2011.6163908
Publikováno v:
6th International Conference on Spoken Language Processing (ICSLP 2000).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58e2f11bba8f135e720e42aef4454c95
https://doi.org/10.21437/icslp.2000-835
https://doi.org/10.21437/icslp.2000-835
Autor:
Don McAllaster, Larry Gillick
Publikováno v:
6th European Conference on Speech Communication and Technology (Eurospeech 1999).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86433baae58220f08c40b441ab8eaa47
https://doi.org/10.21437/eurospeech.1999-358
https://doi.org/10.21437/eurospeech.1999-358
Publikováno v:
HLT
The primary long term goal of speech research at Dragon Systems is to develop algorithms that are capable of achieving very high performance large vocabulary continuous speech recognition. At the same time, in the long run we are also concerned to ke
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53b96039575ca38caf21bb1e06f5bccf
https://doi.org/10.3115/1075812.1075924
https://doi.org/10.3115/1075812.1075924
Publikováno v:
HLT
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the language being spoken. The problem of language identification is often
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46934ceb249051b0acf5a41aede0646f
https://doi.org/10.3115/1075812.1075913
https://doi.org/10.3115/1075812.1075913
Autor:
Robert Roth, James Baker, Janet Baker, Larry Gillick, Melvyn Hunt, Yoshiko Ito, Stephen Lowe, Jeremy Orloff, Barbara Peskin, Francesco Scottone
Publikováno v:
ICASSP (2)
The authors report on the progress that has been made at Dragon Systems in speaker-independent large-vocabulary speech recognition using speech from DARPA's Wall Street Journal corpus. First they present an overview of the recognition and training al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd78c0aafe2c938840b655501fd76800
https://doi.org/10.1109/icassp.1993.319391
https://doi.org/10.1109/icassp.1993.319391
Autor:
Larry Gillick, Stephen Lowe, Melvyn J. Hunt, Yoshiko Ito, Janet M. Baker, John Bridle, James K. Baker, Barbara Peskin, Jeremy Orloff, Robert Roth, Francesco Scattone
Publikováno v:
HLT
In this paper we exhibit a novel approach to the problems of topic and speaker identification that makes use of a large vocabulary continuous speech recognizer. We present a theoretical framework which formulates the two tasks as complementary proble
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef6f6640e2af2ed101f5eff78b8721af
https://doi.org/10.3115/1075671.1075697
https://doi.org/10.3115/1075671.1075697
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