Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Bouselmi, Ghazi"'
Autor:
Bouselmi, Ghazi
La RAP non native souffre encore d'une chute significative de précision. Cette dégradation est due aux erreurs d'accent et de prononciation que produisent les locuteurs non natifs. Les recherches que nous avons entreprises ont pour but d'atténuer
Externí odkaz:
http://www.theses.fr/2008NAN10101/document
Thèse de doctorat : Informatique : Nancy 1 : 2008.
Titre provenant de l'écran-titre.
Titre provenant de l'écran-titre.
Publikováno v:
Dans TAIMA'07, Traitement et Analyse de l'Information : M\'ethodes et Applications (2007)
In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models through integr
Externí odkaz:
http://arxiv.org/abs/0711.1038
Publikováno v:
Dans InterSpeech 2007 (2007)
In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented English speech d
Externí odkaz:
http://arxiv.org/abs/0711.0811
Publikováno v:
Dans ISSPA, International Symposium on Signal Processing and its Applications (2007)
In this paper we present an automated method for the classification of the origin of non-native speakers. The origin of non-native speakers could be identified by a human listener based on the detection of typical pronunciations for each nationality.
Externí odkaz:
http://arxiv.org/abs/0711.0666
Publikováno v:
In Computer Speech & Language 2009 23(2):147-164
Publikováno v:
INTERSPEECH
INTERSPEECH, Sep 2008, Brisbane, Australia
INTERSPEECH, Sep 2008, Brisbane, Australia
International audience; In this article we present a study of a multi-accent and accentindependent non-native speech recognition. We propose several approaches based on phonetic confusion and acoustic adaptation. The goal of this article is to invest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e748c2c905d062785860a3050417a4c1
https://doi.org/10.21437/interspeech.2008-670
https://doi.org/10.21437/interspeech.2008-670
Publikováno v:
Traitement et Analyse de l'Information Méthodes et Applications
Traitement et Analyse de l'Information Méthodes et Applications, May 2007, Hammamet, Tunisie. pp.6
actes de Traitement et Analyse de l'Information Méthodes et Applications
Traitement et Analyse de l'Information Méthodes et Applications, May 2007, Hammamet, Tunisie. pp.6
actes de Traitement et Analyse de l'Information Méthodes et Applications
National audience; Des travaux récents ont été conduits dans le cadre de la reconnaissance automatique de la parole afin d'améliorer les performances des systèmes confrontés à des locuteurs non natifs. Beaucoup de ces systèmes nécessitent la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::96969d0099564d1ba71b346d2cb95049
https://hal.archives-ouvertes.fr/hal-00163756
https://hal.archives-ouvertes.fr/hal-00163756
Autor:
Potamianos, Alexandros, Bouselmi, Ghazi, Dimitriadis, Dimitrios, Fohr, Dominique, Gemello, Roberto, Illina, Irina, Mana, Franco, Maragos, Petros, Matassoni, M., Pitsikalis, Vassilis, Ramirez, J., Sanchez-Soto, E., Segura, J., Svaizer, P.
Publikováno v:
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France
In this paper, we present algorithms for dealing with variability and mismatch in speech recognition due to environmental conditions and non-native speaker populations. The proposed algorithms cover a broad spectrum of ideas including robust feature
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::26e5e4f5d4eef3788eb0dcad4d89954b
https://hal.science/hal-00110502/file/hiwire_sriv06.pdf
https://hal.science/hal-00110502/file/hiwire_sriv06.pdf
Publikováno v:
XXVIes Journées d'Etude sur la Parole-JEP'06
XXVIes Journées d'Etude sur la Parole-JEP'06, Jun 2006, Saint-Malo, France
XXVIes Journées d'Etude sur la Parole-JEP'06, Jun 2006, Saint-Malo, France
This paper presents a fully automated approach for the recognition of non native speech based on acoustic model modification. For a native language (LM) and a spoken language (LP), pronunciation variants of the phones of LP are automatically extracte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::072f2105a17982aaaf15256b7eb37f5a
https://hal.inria.fr/inria-00110495
https://hal.inria.fr/inria-00110495