Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Elloumi, Zied"'
This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to p
Externí odkaz:
http://arxiv.org/abs/1808.08573
In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance
Externí odkaz:
http://arxiv.org/abs/1804.08477
This paper presents an approach combining lexico-semantic resources and distributed representations of words applied to the evaluation in machine translation (MT). This study is made through the enrichment of a well-known MT evaluation metric: METEOR
Externí odkaz:
http://arxiv.org/abs/1610.01291
Publikováno v:
Nephrology Dialysis Transplantation. 35
Background and Aims Arterio-venous fistula (AVF) is considered to be the first choice vascular access for hemodialysis (HD). Hemodialysis catheter (KT) may be a temporary or permanent alternative. The aim of our work was the study of indications, and
Autor:
Elloumi, Zied
Publikováno v:
Automatique. Université Grenoble Alpes, 2019. Français. ⟨NNT : 2019GREAM005⟩
In this thesis, we focus on performance prediction of automatic speech recognition (ASR) systems.This is a very useful task to measure the reliability of transcription hypotheses for a new data collection, when the reference transcription is unavaila
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fbd049fc9523a478fcc32b7de1631c47
https://tel.archives-ouvertes.fr/tel-02173343
https://tel.archives-ouvertes.fr/tel-02173343
Publikováno v:
[Research Report] LIG lab; LNE. 2019
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5613aedffbaf624e9741334e0ef20a74
https://hal.archives-ouvertes.fr/hal-02131931
https://hal.archives-ouvertes.fr/hal-02131931
Publikováno v:
Revue TAL
Revue TAL, ATALA (Association pour le Traitement Automatique des Langues), 2018
Traitement Automatique des Langues
Traitement Automatique des Langues, ATALA, 2018
Revue TAL, ATALA (Association pour le Traitement Automatique des Langues), 2018
Traitement Automatique des Langues
Traitement Automatique des Langues, ATALA, 2018
International audience; Dans ce travail, nous nous intéressons à la tâche de prédiction de performance des systèmes de transcription de la parole. Nous comparons deux approches de prédiction: une approche de l'état de l'art fondée sur l'extra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d3e6142472d053c41f0b82066b203756
https://hal.archives-ouvertes.fr/hal-01976284/document
https://hal.archives-ouvertes.fr/hal-01976284/document
Autor:
Bouzidi, Kamel, Elloumi, Zied, Besacier, Laurent, Lecouteux, Benjamin, Faouzi BenZeghiba, Mohamed
Publikováno v:
Actes de TALN 2017, volume 1
TALN 2017
TALN 2017, Jun 2017, Orléans, France
TALN 2017
TALN 2017, Jun 2017, Orléans, France
International audience; This article presents a new system that automatically translates images of arabic documents. Two modules are involved: an optical character recognition (OCR) module in Arabic and an Arabic-French machine translation module (MT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8bd1086226c8867a269945a4ef4fddfd
https://hal.archives-ouvertes.fr/hal-01623072
https://hal.archives-ouvertes.fr/hal-01623072
Publikováno v:
Actes de la conférence conjointe JEP-TALN-RECITAL
TALN 2016
TALN 2016, Jul 2016, Paris, France
TALN 2016
TALN 2016, Jul 2016, Paris, France
International audience; This paper presents an approach combining lexical-semantic resources and distributed representations of words applied to the evaluation in machine translation (MT). This study is made through the enrichment of a well-known MT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::91065a316430ee4d054b990e5a321932
https://hal.archives-ouvertes.fr/hal-01350101
https://hal.archives-ouvertes.fr/hal-01350101
Publikováno v:
Proceedings of the Summit XV, vol 1
MT Summit 2015
MT Summit 2015, Nov 2015, Miami, United States
MT Summit 2015
MT Summit 2015, Nov 2015, Miami, United States
International audience; This paper proposes an extension of METEOR, a well-known MT evaluation metric, for multiple target languages using an in-house lexical resource called DBnary (an extraction from Wiktionary provided to the community as a Multil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ecac705a7e60ef8aacd59dce8a8ab4b1
https://hal.archives-ouvertes.fr/hal-01350109/document
https://hal.archives-ouvertes.fr/hal-01350109/document