What has LeBenchmark Learnt about French Syntax?

arXiv:2403.02173v1 Announce Type: new
Abstract: 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 translation, spoken language understanding or speech parsing. They are trained on very low level information (the raw speech signal), and do not have explicit lexical knowledge. Despite that, they obtained reasonable results on …

abstract arxiv automatic speech recognition cs.cl french information language language understanding paper recognition reports series speech speech recognition spoken spoken language understanding syntax tasks translation type understanding