← Search

Didier Schwab

9 accepted papers

2024

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

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 4SourcePDFScholar
2024

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

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…

2024

Limitations of Human Identification of Automatically Generated Text

COLING 2024main

Neural text generation is receiving broad attention with the publication of new tools such as ChatGPT. The main reason for that is that the achieved quality of the generated text may be attributed to a human writer by the naked eye of a human evaluator. In this paper, we propose a new corpus in Fren…

2024

Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing

EMNLP 2024finding

Cross-lingual AMR parsing is the task of predicting AMR graphs in a target language when training data is available only in a source language. Due to the small size of AMR training data and evaluation data, cross-lingual AMR parsing has only been explored in a small set of languages such as English,…

2023

Pre-training for Speech Translation: CTC Meets Optimal Transport

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…

2022

Automatic Speech Recognition and Query By Example for Creole Languages Documentation

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…

2021

Lightweight Adapter Tuning for Multilingual Speech Translation

ACL 2021short

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pre-trained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of task-specific trainable parameters.…

2021

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

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 41SourceScholar
2020

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

COLING 2020main

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for on…