← Authors

Laurent Besacier

61 papers · 2016–2025 · 8 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🐝 Cross-Pollinator (14) πŸƒ Academic Marathon (9) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (18) 🌟 Keyword Trendsetter Combo (3) 🏠 Conference Loyalist (21) πŸ”¬ Deep Specialist (16) πŸ† Keyword Champion (2) 🧬 Topic Evolution πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (10) ⚑ Prolific Year (12) πŸ—ƒοΈ Keyword Collector (52) πŸ’Ž Century Club (61) ❓ The Questioner (5)

Conferences

INTERSPEECH (21) EMNLP (12) ACL (10) COLING (8) CONLL (4) IJCNLP (3) EACL (2) SEMEVAL (1)

Top co-authors

Didier Schwab (9) Alexandre Berard (7) Ioan Calapodescu (7) Marcely Zanon Boito (6) Vassilina Nikoulina (6) Yannick Estève (5) Maha Elbayad (5) Benjamin Lecouteux (4) Ha Nguyen (4) Jakob Verbeek (4)

Research topics

Linguistics (2) Education (1)

Keywords

automatic speech recognition (13) neural machine translation (9) speech translation (8) low-resource language (8) speech recognition (7) machine translation (6) speech processing (5) gender bia (4) word segmentation (4) self-supervised learning (4) transfer learning (4) recurrent neural network (4) text-to-speech synthesis (4) word embedding (3) context-aware translation (3) multilingual speech (3) unsupervised learning (3) speech synthesis (3) multilingual translation (3) representation learning (3)

Papers

Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection COLING 2025
NAVER LABS Europe Submission to the Instruction-following Track ACL 2025
ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models COLING 2025
mHuBERT-147: A Compact Multilingual HuBERT Model INTERSPEECH 2024
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond INTERSPEECH 2024
Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation EACL 2023
Fashioning Local Designs from Generic Speech Technologies in an Australian Aboriginal Community COLING 2022
Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models ACL 2022
Learning From Failure: Data Capture in an Australian Aboriginal Community ACL 2022
Focused Concatenation for Context-Aware Neural Machine Translation EMNLP 2022
SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages EMNLP 2022
ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks INTERSPEECH 2022
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model INTERSPEECH 2022
What Do Compressed Multilingual Machine Translation Models Forget? EMNLP 2022
A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems INTERSPEECH 2022
Weakly Supervised Word Segmentation for Computational Language Documentation ACL 2022
Using ASR-Generated Text for Spoken Language Modeling ACL 2022
Visualizing Cross‐Lingual Discourse Relations in Multilingual TED Corpora EMNLP 2021
Findings of the WMT Shared Task on Machine Translation Using Terminologies EMNLP 2021
Lightweight Adapter Tuning for Multilingual Speech Translation IJCNLP 2021
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? IJCNLP 2021
Lightweight Adapter Tuning for Multilingual Speech Translation ACL 2021
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? ACL 2021
Investigating the Impact of Gender Representation in ASR Training Data: a Case Study on Librispeech ACL 2021
Controlling Prosody in End-to-End TTS: A Case Study on Contrastive Focus Generation CONLL 2021
Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input INTERSPEECH 2021
Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation INTERSPEECH 2021
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech INTERSPEECH 2021
Investigating the Impact of Gender Representation in ASR Training Data: a Case Study on Librispeech IJCNLP 2021
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters EMNLP 2021
Controlling Prosody in End-to-End TTS: A Case Study on Contrastive Focus Generation EMNLP 2021
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English COLING 2020
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020 ACL 2020
Enabling Interactive Transcription in an Indigenous Community COLING 2020
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation COLING 2020
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech CONLL 2020
Monolingual Adapters for Zero-Shot Neural Machine Translation EMNLP 2020
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech EMNLP 2020
What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTS INTERSPEECH 2020
Efficient Wait-k Models for Simultaneous Machine Translation INTERSPEECH 2020
Investigating Self-Supervised Pre-Training for End-to-End Speech Translation INTERSPEECH 2020
Modeling ASR Ambiguity for Neural Dialogue State Tracking INTERSPEECH 2020
The Zero Resource Speech Challenge 2020: Discovering Discrete Subword and Word Units INTERSPEECH 2020
Empirical Evaluation of Sequence-to-Sequence Models for Word Discovery in Low-Resource Settings INTERSPEECH 2019
Naver Labs Europe’s Systems for the Document-Level Generation and Translation Task at WNGT 2019 EMNLP 2019
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech CONLL 2019
The Zero Resource Speech Challenge 2019: TTS Without T INTERSPEECH 2019
Adaptor Grammars for the Linguist: Word Segmentation Experiments for Very Low-Resource Languages EMNLP 2018
Unsupervised Word Segmentation from Speech with Attention INTERSPEECH 2018
Analyzing Learned Representations of a Deep ASR Performance Prediction Model EMNLP 2018
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction CONLL 2018
Token-level and sequence-level loss smoothing for RNN language models ACL 2018
Machine Assisted Analysis of Vowel Length Contrasts in Wolof INTERSPEECH 2017
CompiLIG at SemEval-2017 Task 1: Cross-Language Plagiarism Detection Methods for Semantic Textual Similarity SEMEVAL 2017
Using Word Embedding for Cross-Language Plagiarism Detection EACL 2017
Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks COLING 2016
Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources? COLING 2016
Lig-Aikuma: A Mobile App to Collect Parallel Speech for Under-Resourced Language Studies INTERSPEECH 2016
Better Evaluation of ASR in Speech Translation Context Using Word Embeddings INTERSPEECH 2016
Speed Perturbation and Vowel Duration Modeling for ASR in Hausa and Wolof Languages INTERSPEECH 2016
Preliminary Experiments on Unsupervised Word Discovery in Mboshi INTERSPEECH 2016