Výsledky vyhledávání - "Sahar Ghannay"

A study of continuous space word and sentence representations applied to ASR error detection

Autor: Nathalie Camelin, Yannick Estève, Sahar Ghannay

Publikováno v: Speech Communication
Speech Communication, Elsevier : North-Holland, 2020

International audience; This paper presents a study of continuous word representations applied to automatic detection of speech recognition errors. A neural network architecture is proposed, which is well suited to handle continuous word representati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01ceadc2d8a585db956ed3684db37275
https://doi.org/10.1016/j.specom.2020.03.002

Zobrazit plný text záznamu

OVERLAP-AWARE LOW-LATENCY ONLINE SPEAKER DIARIZATION BASED ON END-TO-END LOCAL SEGMENTATION

Autor: Juan Manuel Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

Publikováno v: IEEE Automatic Speech Recognition and Unserstanding Workshop
IEEE Automatic Speech Recognition and Unserstanding Workshop, Dec 2021, Cartagena, Colombia
HAL

We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms. Every single step of the proposed pipeline is designed to take full advantage of the st

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba4cf6e9a7543c81631b1534e5f4da81
https://hal.archives-ouvertes.fr/hal-03375330/file/this-paper.pdf

Zobrazit plný text záznamu

Where are we in semantic concept extraction for Spoken Language Understanding? ⋆

Autor: Gaëlle Laperrière, Salima Mdhaffar, Sahar Ghannay, Bassam Jabaian, Antoine Caubrière, Yannick Estève

Publikováno v: SPECOM 2021 23rd International Conference on Speech and Computer
SPECOM 2021 23rd International Conference on Speech and Computer, Sep 2021, Saint Petersburg, Russia
Speech and Computer ISBN: 9783030878016
SPECOM

Spoken language understanding (SLU) topic has seen a lot of progress these last three years, with the emergence of end-to-end neural approaches. Spoken language understanding refers to natural language processing tasks related to semantic extraction

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aafa9337fffa958fa34908d411b1629a
https://hal.science/hal-03372494/document

Zobrazit plný text záznamu

LIMSI_UPV at SemEval-2020 Task 9: Recurrent Convolutional Neural Network for Code-mixed Sentiment Analysis

Autor: Sahar Ghannay, Paolo Rosso, Anne Vilnat, Somnath Banerjee, Sophie Rosset

Publikováno v: HAL
SemEval@COLING

This paper describes the participation of LIMSI UPV team in SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text. The proposed approach competed in SentiMix Hindi-English subtask, that addresses the problem of predicting the senti

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f00ffa973d3ffb59bff7d18b5af26f5
https://hal.archives-ouvertes.fr/hal-03294371

Zobrazit plný text záznamu

Lifelong Learning and Task-Oriented Dialogue System: What Does It Mean?

Autor: Mathilde Veron, Sahar Ghannay, Sophie Rosset, Anne-Laure Ligozat

Publikováno v: Lecture Notes in Electrical Engineering ISBN: 9789811593222
IWSDS
International Workshop on Spoken Dialogue Systems Technology
International Workshop on Spoken Dialogue Systems Technology, Apr 2019, Siracusa, Italy
HAL

International audience; The main objective of this paper is to propose a functional definition of lifelong learning system adapted to the framework of task-oriented system. We mainly identified two aspects where a lifelong learning technology could b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3bb08b7bee22dd4eb0bfeaa45e7f1e4
https://doi.org/10.1007/978-981-15-9323-9_32

Zobrazit plný text záznamu

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification

Autor: Sophie Rosset, Sahar Ghannay, Hervé Bredin, Juan Manuel Coria

Publikováno v: International Conference on Statistical Language and Speech Processing
International Conference on Statistical Language and Speech Processing, Oct 2020, Cardiff, United Kingdom. pp.137-148, ⟨10.1007/978-3-030-59430-5_11⟩
Statistical Language and Speech Processing ISBN: 9783030594299
SLSP

Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification. We try to fill this gap and compare several metric learning loss functions in a sy

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e07e78fbc99e43d506fa11103aef5e4
https://hal.archives-ouvertes.fr/hal-02989334

Zobrazit plný text záznamu

A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning Scenarios

Autor: Sahar Ghannay, Guillermo Echegoyen, Anselmo Peñas, Mathilde Veron, Somnath Banerjee, Sophie Rosset

Publikováno v: Natural Language Processing and Information Systems ISBN: 9783030513092
NLDB
HAL
Natural Language Processing and Information Systems
International Conference on Applications of Natural Language to Information Systems
International Conference on Applications of Natural Language to Information Systems, Elisabeth Métais and Farid Meziane and Helmut Horacek and Philipp Cimiano, Jun 2020, SaarbrÃ¼cken, Germany

International audience; In a long term exploitation environment, a Question Answering (QA) system should maintain or even improve its performance over time, trying to overcome the lacks made evident through the interactions with users. We claim that,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a62928dc57bbffcee1c05f06a081eb5a
https://doi.org/10.1007/978-3-030-51310-8_9

Zobrazit plný text záznamu

A Metric Learning Approach to Misogyny Categorization

Autor: Sahar Ghannay, Sophie Rosset, Hervé Bredin, Juan Manuel Coria

Publikováno v: RepL4NLP@ACL
Proceedings of the 5th Workshop on Representation Learning for NLP
Workshop on Representation Learning for NLP
Workshop on Representation Learning for NLP, Jul 2020, Online, France. pp.89-94, ⟨10.18653/v1/2020.repl4nlp-1.12⟩

International audience; The task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions. I

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28c512651ff091c4d6620c8e8ef423bd
https://doi.org/10.18653/v1/2020.repl4nlp-1.12

Zobrazit plný text záznamu

Error analysis applied to end-to end spoken language understanding

Autor: Yannick Estève, Sahar Ghannay, Antoine Caubrière, Emmanuel Morin, Natalia A. Tomashenko, Renato De Mori, Antoine Laurent

Publikováno v: ICASSP
45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2020, Barcelona, Spain

This paper presents a qualitative study of errors produced by an end-to-end spoken language understanding (SLU) system (speech signal to concepts) that reaches state of the art performance. Different studies are proposed to better understand the weak

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f33b81ffbab8685ab7ad5b957ed23b0
https://hal.science/hal-02465899

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání