136 citations
- Centre National de la Recherche ScientifiqueFR31 papers
- Le Mans UniversitéFR18 papers
- Nantes UniversitéFR12 papers
- Université d'AngersFR10 papers
- Laboratoire des Sciences du Numérique de NantesFR6 papers
- École Centrale de NantesFR5 papers
- Laboratoire Informatique d'AvignonFR5 papers
- Institut de recherche en communications et cybernétique de NantesFR4 papers
- Institut des Sciences et Technologies Moléculaires d'AngersFR4 papers
- Institut Supérieur des Matériaux du MansFR4 papers
- Laboratoire de Planétologie et GéosciencesFR4 papers
- InsermFR3 papers
11 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…
Disagreement as Data: Reasoning Trace Analytics in Multi-Agent Systems
Elham Tajik, Conrad Borchers, Bahar Shahrokhian +4
Learning analytics researchers often analyze qualitative student data such as coded annotations or interview transcripts to understand learning processes. With the rise of generati…
Direct Text to Speech Translation System using Acoustic Units
Victoria Mingote, Pablo Gimeno, Luis Vicente +3
This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech…
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
Sameer Khurana, Antoine Laurent, James Glass
We propose a simple and effective cross-lingual transfer learning method to adapt monolingual wav2vec-2.0 models for Automatic Speech Recognition (ASR) in resource-scarce languages…