![lbesacie](https://europe.naverlabs.com/wp-content/uploads/2018/11/img-head-user-1.jpg)
This user has not added any information to their profile yet.
- Speech-MASSIVE: a multilingual speech dataset for SLU and beyond
The 25th Interspeech Conference, Kos Island, Greece, 1-5 September, 2024
- LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech
ScienceDirect, Computer Speech & Language journal, Volume 86, June, 2024
- ELITR-Bench: a meeting assistant benchmark for long-context language models
Workshop on Long-Context Foundation Models, ICML, Vienna, Austria, 26 July, 2024
- Encoding sentence position in context-aware neural machine translation with concatenation
The Fourth Workshop on Insights from Negative Results in NLP (Insights 2023), Dubrovnik, Croatia, 2–6 June, 2023
- Focused concatenation for context-aware neural machine translation
7th Conference on Machine Translation (WMT) at the Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, United Arab Emirates, 7-9 December, 2022
- What do compressed multilingual machine translation models forget?
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, United Arab Emirates, 7-9 December, 2022
- SMaLL-100: introducing shallow multilingual machine translation model for low-resource languages
Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, United Arab Emirates, 7-9 December, 2022
- A Textless Metric for Speech-to-Speech Comparison
Published on arXiv.org
- A study of gender impact in self-supervised models for speech-to-text systems
INTERSPEECH 2022, Incheon, Korea, 18-22 September, 2022
- ASR-generated text for language model pre-training applied to speech tasks
Published on arXiv.org
- Weakly supervised word segmentation for computational language documentation
60th Annual Meeting of the Association for Computational Linguistics (ACL), Dublin, Ireland, 22-27 May, 2022
- What do compressed multilingual machine translation models forget?
Published on arXiv.org, 22 May, 2022
- Divide and rule: effective pre-training for context-aware multi-encoder translation models
60th Annual Meeting of the Association for Computational Linguistics (ACL), Dublin, Ireland, 22-27 May, 2022
- Task agnostic and task specific self-supervised learning from speech with LeBenchmark
Neural Information Processing Systems (NeurIPS), virtual event, 6-14 December, 2021
- Controlling prosody in end-to-end TTS: a case study on contrastive focus generation
The SIGNLL Conference on Computational Natural Language Learning (CoNLL), co-located with EMNLP, 10-11 November, 2021
- Findings of the WMT shared task on machine translation using terminologies
6th Conference on Machine Translation (WMT), co-located with the Conference on Empirical Methods in Natural Language Processing (EMNLP), 7-11 November, 2021
- Multilingual unsupervised neural machine translation with denoising adapters
Conference on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic (hybrid event), 7-11 November, 2021
- Alternate endings: improving prosody for incremental neural TTS with predicted future text input
Interspeech, Brno, Czech Republic, 30 August - 3 September, 2021
- LeBenchmark: a reproducible framework for assessing self-supervised representation learning from speech
Interspeech, Brno, Czech Republic, 30 August - 3 September, 2021
- Lightweight adapter tuning for multilingual speech translation
The Annual Meeting of the Association for Computation Linguistics (ACL) 2021, virtual event, 1-6 August, 2021
- Do multilingual neural machine translation models contain language pair specific attention heads?
Findings of the Annual Meeting of the Association for Computation Linguistics (ACL) 2021, virtual event, 1-6 August, 2021
- Impact of encoding and segmentation strategies on end-to-end simultaneous speech translation
Interspeech, Brno, Czech Republic, 30 August - 3 September, 2021
- On the evaluation of machine translation for terminology consistency
Published on arXiv.org, 22 June 2021
- An empirical study of end-to-end simultaneous speech translation decoding strategies
The International Conference on Acoustics, Speech, & Signal Processing (ICASSP), Toronto, Canada, 6-11 June, 2021
- Fast development of ASR in African languages using self supervised speech representation learning
AfricaNLP Workshop at the European Chapter of the Association for Computational Linguistics conference (EACL), virtual event, 19 April, 2021