Benjamin Lecouteux — accepted AI-conference papers

2024

A Multimodal French Corpus of Aligned Speech, Text, and Pictogram Sequences for Speech-to-Pictogram Machine Translation

Cécile Macaire, Chloé Dion, Jordan Arrigo, Claire Lemaire, Emmanuelle Esperança-Rodier, Benjamin Lecouteux +1

COLING 2024main

The automatic translation of spoken language into pictogram units can facilitate communication involving individuals with language impairments. However, there is no established translation formalism or publicly available datasets for training end-to-end speech translation systems. This paper introdu…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech

Adrien Pupier, Maximin Coavoux, Jérôme Goulian, Benjamin Lecouteux

ACL 2024short

Direct dependency parsing of the speech signal –as opposed to parsing speech transcriptions– has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of usin…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Jargon: A Suite of Language Models and Evaluation Tasks for French Specialized Domains

Vincent Segonne, Aidan Mannion, Laura Cristina Alonzo Canul, Alexandre Daniel Audibert, Xingyu Liu, Cécile Macaire +20

COLING 2024main

Pretrained Language Models (PLMs) are the de facto backbone of most state-of-the-art NLP systems. In this paper, we introduce a family of domain-specific pretrained PLMs for French, focusing on three important domains: transcribed speech, medicine, and law. We use a transformer architecture based on…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

What Has LeBenchmark Learnt about French Syntax?

Zdravko Dugonjić, Adrien Pupier, Benjamin Lecouteux, Maximin Coavoux

COLING 2024main

The paper reports on a series of experiments aiming at probing LeBenchmark, a pretrained acoustic model trained on 7k hours of spoken French, for syntactic information. Pretrained acoustic models are increasingly used for downstream speech tasks such as automatic speech recognition, speech translati…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Pre-training for Speech Translation: CTC Meets Optimal Transport

Phuong-Hang Le, Hongyu Gong, Changhan Wang, Juan Pino, Benjamin Lecouteux, Didier Schwab

ICML 2023oral

The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we propose to mitigate this issue at the pre-training stage, requi…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2022

Automatic Speech Recognition and Query By Example for Creole Languages Documentation

Cécile Macaire, Didier Schwab, Benjamin Lecouteux, Emmanuel Schang

ACL 2022findings

We investigate the exploitation of self-supervised models for two Creole languages with few resources: Gwadloupéyen and Morisien. Automatic language processing tools are almost non-existent for these two languages. We propose to use about one hour of annotated data to design an automatic speech reco…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2021

Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark

Solène Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir +12

NeurIPS 2021poster

Self-Supervised Learning (SSL) has yielded remarkable improvements in many different domains including computer vision, natural language processing and speech processing by leveraging large amounts of unlabeled data. In the specific context of speech, however, and despite promising results, there ex…

Cited by 41 Source ↗Scholar ↗

2018

ASR Performance Prediction on Unseen Broadcast Programs Using Convolutional Neural Networks

Zied Elloumi, Laurent Besacier, Olivier Galibert, Juliette Kahn, Benjamin Lecouteux

ICASSP 2018accepted

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 prediction based on regression (engineered featur…

Cited by 0 Source ↗Scholar ↗