Spoken language understanding (SLU) topic has seen a lot of progress these
last three years, with the emergence of end-to-end neural approaches. Spoken
language understanding refers to natural language processing tasks related to
semantic extraction from speech signal, like named entity recognition from
speech or slot filling task in a context of human-machine dialogue.
Classically, SLU tasks were processed through a cascade approach that consists
in applying, firstly, an automatic speech recognition process, followed by a
natural language processing module applied to the automatic transcriptions.
These three last years, end-to-end neural approaches, based on deep neural
networks, have been proposed in order to directly extract the semantics from
speech signal, by using a single neural model. More recent works on
self-supervised training with unlabeled data open new perspectives in term of
performance for automatic speech recognition and natural language processing.
In this paper, we present a brief overview of the recent advances on the French
MEDIA benchmark dataset for SLU, with or without the use of additional data. We
also present our last results that significantly outperform the current
state-of-the-art with a Concept Error Rate (CER) of 11.2%, instead of 13.6% for
the last state-of-the-art system presented this year.

本文述及基于最近三年的神经网络技术，通过直接从语音信号中提取语义，取代传统的分类式自然语言处理方式，以 spoken language understanding 话题研究为主，在利用未标记的数据进行自我监督训练方面取得了新的突破。同时介绍了针对法语 MEDIA 数据集的最新进展，并提出了得到明显改进的成果，概念误差率（CER）从现有最优系统的 13.6% 降至 11.2%。