3 papers
cs.CL2024
Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech
Adrien Pupier, Maximin Coavoux, Jérôme Goulian +1
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 incorporatin…
cs.CL2024
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Titouan Parcollet, Ha Nguyen, Solene Evain +19
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing…
cs.CL2024
What has LeBenchmark Learnt about French Syntax?
Zdravko DugonjiÄ, Adrien Pupier, Benjamin Lecouteux +1
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…