Search Results for author: Mickael Rouvier

Found 24 papers, 3 papers with code

Far-Field Speaker Recognition Benchmark Derived From The DiPCo Corpus

no code implementations LREC 2022 Mickael Rouvier, Mohammad Mohammadamini

The main goal of this corpus is to foster research in far-field and multi-channel text-independent speaker verification.

Denoising Speaker Recognition +2

Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2

no code implementations28 Mar 2024 Pierre-Michel Bousquet, Mickael Rouvier

The SdSv challenge Task 2 provided an opportunity to assess efficiency and robustness of modern text-independent speaker verification systems.

Speaker Recognition Task 2 +1

Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems

no code implementations29 Feb 2024 Quentin Raymondaud, Mickael Rouvier, Richard Dufour

Following many researches in neural networks interpretability, we propose in this article a protocol that aims to determine which and where information is located in an ASR acoustic model (AM).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

How Important Is Tokenization in French Medical Masked Language Models?

no code implementations22 Feb 2024 Yanis Labrak, Adrien Bazoge, Beatrice Daille, Mickael Rouvier, Richard Dufour

Subword tokenization has become the prevailing standard in the field of natural language processing (NLP) over recent years, primarily due to the widespread utilization of pre-trained language models.

DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain

1 code implementation20 Feb 2024 Yanis Labrak, Adrien Bazoge, Oumaima El Khettari, Mickael Rouvier, Pacome Constant dit Beaufils, Natalia Grabar, Beatrice Daille, Solen Quiniou, Emmanuel Morin, Pierre-Antoine Gourraud, Richard Dufour

This limitation hampers the evaluation of the latest French biomedical models, as they are either assessed on a minimal number of tasks with non-standardized protocols or evaluated using general downstream tasks.

named-entity-recognition Named Entity Recognition +3

A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks

no code implementations22 Jul 2023 Yanis Labrak, Mickael Rouvier, Richard Dufour

We evaluate four state-of-the-art instruction-tuned large language models (LLMs) -- ChatGPT, Flan-T5 UL2, Tk-Instruct, and Alpaca -- on a set of 13 real-world clinical and biomedical natural language processing (NLP) tasks in English, such as named-entity recognition (NER), question-answering (QA), relation extraction (RE), etc.

named-entity-recognition Named Entity Recognition +3

DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains

no code implementations3 Apr 2023 Yanis Labrak, Adrien Bazoge, Richard Dufour, Mickael Rouvier, Emmanuel Morin, Béatrice Daille, Pierre-Antoine Gourraud

In recent years, pre-trained language models (PLMs) achieve the best performance on a wide range of natural language processing (NLP) tasks.

Studying squeeze-and-excitation used in CNN for speaker verification

no code implementations13 Sep 2021 Mickael Rouvier, Pierre-Michel Bousquet

A channel attention mechanism, called squeeze-and-excitation (SE), has recently been proposed in convolution layers and applied to speaker verification.

Speaker Verification

Study on the temporal pooling used in deep neural networks for speaker verification

no code implementations10 May 2021 Mickael Rouvier, Pierre-Michel Bousquet, Jarod Duret

The x-vector architecture has recently achieved state-of-the-art results on the speaker verification task.

Speaker Verification

ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task

no code implementations EMNLP (IWSLT) 2019 Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubriere, Fethi Bougares, Mickael Rouvier, Laurent Besacier, Yannick Esteve

This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English-to-Portuguese language pair.


Fusion d'espaces de repr\'esentations multimodaux pour la reconnaissance du r\^ole du locuteur dans des documents t\'el\'evisuels (Multimodal embedding fusion for robust speaker role recognition in video broadcast )

no code implementations JEPTALNRECITAL 2016 Sebastien Delecraz, Frederic Bechet, Benoit Favre, Mickael Rouvier

L{'}identification du r{\^o}le d{'}un locuteur dans des {\'e}missions de t{\'e}l{\'e}vision est un probl{\`e}me de classification de personne selon une liste de r{\^o}les comme pr{\'e}sentateur, journaliste, invit{\'e}, etc.

Cannot find the paper you are looking for? You can Submit a new open access paper.