Spoken Language Understanding consists in extracting semantic information conveyed by speech signal in order to project it into a representation manageable by a software application. This research topic encompasses several tasks like domain classification, named entity recognition, slot filling… By some aspects, it is also very close to machine translation. SLU has been encouraged by NIST effort during the 90’s and during the last three decades different recurrent issues has been addressed. This presentation will present a brief overview of the main research work done during this period, in order to better understand the benefits of the recent single neural end-to-end system that extract semantics directly from speech.
