Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Mohamed Faouzi BenZeghiba"'
Autor:
Christophe Ris, D. Jouvet, Richard Rose, R. De Mori, Mohamed Faouzi BenZeghiba, Pietro Laface, Christian Wellekens, Olivier Deroo, Vivek Tyagi, Stéphane Dupont, T. Erbes, Luciano Fissore, Alfred Mertins
Publikováno v:
Speech Communication
Speech Communication, Elsevier : North-Holland, 2007, ⟨10.1016/j.specom.2007.02.006⟩
Speech Communication, Elsevier : North-Holland, 2007, ⟨10.1016/j.specom.2007.02.006⟩
International audience; Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3db5655a526c4e20c54e88be24978efa
https://doi.org/10.1016/j.specom.2007.02.006
https://doi.org/10.1016/j.specom.2007.02.006
Publikováno v:
Speech Communication. 48:1200-1213
This paper discusses and optimizes an HMM/GMM based User-Customized Password Speaker Verification (UCP-SV) system. Unlike text-dependent speaker verification, in UCP-SV systems, customers can choose their own passwords with no lexical constraints. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b0f6bbcf9036275406bdbd9ba47a20a
https://doi.org/10.1016/j.specom.2005.08.008
https://doi.org/10.1016/j.specom.2005.08.008
Autor:
Ronaldo Messina, Maxime Knibbe, Jérôme Louradour, Theodore Bluche, Christopher Kermorvant, Bastien Moysset, Mohamed Faouzi BenZeghiba
Publikováno v:
ICFHR
This paper describes the system submitted by A2iA to the second Maurdor evaluation for multi-lingual text recogni- tion. A system based on recurrent neural networks and weighted finite state transducers was used both for printed and handwritten recog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c84b74000e8bc88f15167f9990db25c
https://doi.org/10.1109/icfhr.2014.57
https://doi.org/10.1109/icfhr.2014.57
Autor:
Christopher Kermorvant, Maxime Knibbe, Jérôme Louradour, Bastien Moysset, Mohamed Faouzi BenZeghiba, Theodore Bluche
Publikováno v:
Document Analysis Systems
This paper describes the Arabic handwriting recognition systems proposed by A2iA to the NIST OpenHaRT2013 evaluation. These systems were based on an optical model using Long Short-Term Memory (LSTM) recurrent neural networks, trained to recognize the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f0c237712745e303e5a0e67527f6104
https://doi.org/10.1109/das.2014.40
https://doi.org/10.1109/das.2014.40
Publikováno v:
INTERSPEECH
Annual Conference of the International Speech Communication Association
Annual Conference of the International Speech Communication Association, ISCA, Sep 2012, Portland, OR, United States
Annual Conference of the International Speech Communication Association
Annual Conference of the International Speech Communication Association, ISCA, Sep 2012, Portland, OR, United States
International audience; This paper describes a very efficient Parallel Phone Recognizersfollowed by Language Modeling (PPRLM) system in terms of bothperformance and processing speed. The system uses context-independentphone recognizers trained on MLP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79a68805e3c9eef93b2174687084fc77
https://doi.org/10.21437/interspeech.2012-545
https://doi.org/10.21437/interspeech.2012-545
Publikováno v:
Interspeech 2010.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ed2284ecca1fa0c4f2e9f907dfacc1b
https://doi.org/10.21437/interspeech.2010-718
https://doi.org/10.21437/interspeech.2010-718
Publikováno v:
INTERSPEECH
Generative Gaussian back-end and discriminative logistic regression are the most used approaches for language score fusion and calibration. Combination of these two approaches can significantly improve the performance. This paper proposes the use of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1374aecd99168c9543c991cee66b50a
https://doi.org/10.21437/interspeech.2009-624
https://doi.org/10.21437/interspeech.2009-624
Publikováno v:
ICASSP
This paper proposes a new approach to the challenging open-set language detection task. Most state-of-the-art approaches make use of data sources with several out-of-set languages to model such languages. In the proposed approach, no additional data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28622f0b125cb49ac0188d9cf7eff4d2
https://doi.org/10.1109/icassp.2009.4960592
https://doi.org/10.1109/icassp.2009.4960592
Publikováno v:
INTERSPEECH
The performance of a PPRLM language recognition system depends on the quality and the consistency of phone decoders. To improve the performance of the decoders, this paper investigates the use of context-dependent instead of contextindependent phone
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::579e1e6ad08658a2b0e86458204bfd2c
https://doi.org/10.21437/interspeech.2008-142
https://doi.org/10.21437/interspeech.2008-142
Publikováno v:
INTERSPEECH
This paper investigates a new approach to perform simultaneous speech and speaker recognition. The likelihood estimated by a speaker identification system is combined with the posterior probability estimated by the speech recognizer. So, the joint po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d84e79f7b3e7ec68b20bc249c48a9f10
https://doi.org/10.21437/interspeech.2004-527
https://doi.org/10.21437/interspeech.2004-527