From the 4 of 35 papers with an AI index.
50 citations
- IMT AtlantiqueFR11 papers
- Laboratoire de Physique Subatomique et des Technologies AssociéesFR10 papers
- Laboratoire des Sciences du Numérique de NantesFR10 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Le Mans UniversitéFR5 papers
- Laboratoire de Mathématiques Jean LerayFR4 papers
- Centre de physique des particules de MarseilleFR3 papers
- École Centrale de NantesFR3 papers
- École Nationale Supérieure d'Ingénieurs de CaenFR3 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR3 papers
- Institut Pluridisciplinaire Hubert CurienFR3 papers
- Laboratoire de Physique Corpusculaire de CaenFR3 papers
3 papers · 1 filter
A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa +1
The performance of end-to-end automatic speech recognition (ASR) systems enables their increasing integration into numerous applications. While there are various benefits to such s…
A Paradigm for Interpreting Metrics and Identifying Critical Errors in Automatic Speech Recognition
Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa +1
The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their p…
HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics
Thibault Bañeras Roux, Jane Wottawa, Mickael Rouvier +2
Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word e…