Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Abdelkhalek Messaoudi"'
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d85626560b4857e3a023dc995c55f8ed
https://doi.org/10.21437/interspeech.2016-180
https://doi.org/10.21437/interspeech.2016-180
Publikováno v:
2016 International Conference on Electrical and Information Technologies (ICEIT).
In this study, the control of the inverter power system and the fuel cell production system secured the main behavior of the distributed generation on the grid power injection. The deadbeat control strategy allows high control flexibility and capabil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2fe3001d4b0f81236aa1bd9923e34c69
https://doi.org/10.1109/eitech.2016.7519573
https://doi.org/10.1109/eitech.2016.7519573
Publikováno v:
ACM Transactions on Asian Language Information Processing. 8:1-18
The Arabic language presents a number of challenges for speech recognition, arising in part from the significant differences in the spoken and written forms, in particular the conventional form of texts being non-vowelized. Being a highly inflected l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f08c23e7d7b92fa239f3b6aa4c4b463f
https://doi.org/10.1145/1644879.1644885
https://doi.org/10.1145/1644879.1644885
Autor:
Jean-Luc Gauvain, Viet Bac Le, Lori Lamel, Antoine Laurent, Abdelkhalek Messaoudi, Thiago Fraga-Silva
Publikováno v:
INTERSPEECH
Interspeech 2015
Interspeech 2015, Sep 2015, Dresden, Germany
Interspeech 2015
Interspeech 2015, Sep 2015, Dresden, Germany
This paper presents first results in using active learning (AL) for training data selection in the context of the IARPABabel program. Given an initial training data set, we aim to automatically select additional data (from an untranscribed pool data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d3972d881e8bc49697e1f60e5f9ca8f
https://doi.org/10.21437/interspeech.2015-636
https://doi.org/10.21437/interspeech.2015-636
Autor:
Viet Bac Le, Lori Lamel, Cécile Woehrling, Anindya Roy, Julien Despres, Jean-Luc Gauvain, William Hartmann, Abdelkhalek Messaoudi
Publikováno v:
INTERSPEECH
This paper presents recent progress in developing speech-totext (STT) and keyword spotting (KWS) systems for the 2014 IARPA-Babel evaluation. Systems have been developed for the limited language pack condition for four of the five development languag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8fec6efd76961329839ac93e027bbe78
https://doi.org/10.21437/interspeech.2014-527
https://doi.org/10.21437/interspeech.2014-527
Publikováno v:
INTERSPEECH
Annual Conference of the International Speech Communication Association
Annual Conference of the International Speech Communication Association, ISCA, Sep 2014, Singapore, Singapore
Annual Conference of the International Speech Communication Association
Annual Conference of the International Speech Communication Association, ISCA, Sep 2014, Singapore, Singapore
International audience; For languages with limited training resources, out-of-vocabulary (OOV) words are a significant problem, both fortranscription and keyword spotting. This paper investigates theuse of subword lexical units for keyword spotting.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3652ee15719193b901d2db15c348daf
https://doi.org/10.21437/interspeech.2014-528
https://doi.org/10.21437/interspeech.2014-528
Publikováno v:
INTERSPEECH
One of the challenges of Arabic speech recognition is to deal with the huge lexical variety. Morphological decomposition has been proposed to address this problem by increasing lexical coverage, thereby reducing errors that are due to words that are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e58d734ef7de1f30e603826caa53d418
https://doi.org/10.21437/interspeech.2008-413
https://doi.org/10.21437/interspeech.2008-413
Publikováno v:
INTERSPEECH
This paper summarizes our recent progress in improving theautomatic transcription of Arabic broadcast audio data, andsome efforts to address the challenges of the broadcast con-versational speech. Our efforts are aimed at improving theacoustic, pronu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5349b0548b55785d8beded5bd16bebd1
https://doi.org/10.21437/interspeech.2007-562
https://doi.org/10.21437/interspeech.2007-562
Autor:
Kai Yu, Abdelkhalek Messaoudi, Jean-Luc Gauvain, Lori Lamel, Xunying Liu, Rohit Sinha, Philip C. Woodland, K. Nguyen, Long Nguyen, Tim Ng, Mark J. F. Gales, Spyros Matsoukas
Publikováno v:
ICASSP (4)
The majority of state-of-the-art speech recognition systems make use of system combination. The combination approaches adopted have traditionally been tuned to minimising word error rates (WERs). In recent years there has been a growing interest in t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36b8f38907d51a43761a71f1b315da4d
https://doi.org/10.1109/icassp.2007.367310
https://doi.org/10.1109/icassp.2007.367310
Publikováno v:
ICASSP (1)
Recently it has been shown that modeling short vowels in Arabic can significantly improve performance even when producing a non-vocalized transcript. Since Arabic texts and audio transcripts are almost exclusively non-vocalized, the training methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d4bdb38f62083bffa4aa4e4ff1ef686
https://doi.org/10.1109/icassp.2006.1660215
https://doi.org/10.1109/icassp.2006.1660215