论文标题
Vers lacompréhensionde la paromique d parole bout-en-bout-en moindre努力
Vers la compréhension automatique de la parole bout-en-bout à moindre effort
论文作者
论文摘要
口语理解的最新进展受益于接受大型语音语料库训练的自制模型。对于法国人来说，Lebenchmark项目使此类模型可用，并在包括口语理解在内的几项任务上取得了令人印象深刻的进步。这些进步在计算时间和能耗方面具有不可忽略的成本。在本文中，我们比较了几种旨在降低这种成本同时保持竞争性能的学习策略。实验是在媒体语料库上进行的，并表明可以在保持最先进的表演的同时降低学习成本。
Recent advances in spoken language understanding benefited from Self-Supervised models trained on large speech corpora. For French, the LeBenchmark project has made such models available and has led to impressive progress on several tasks including spoken language understanding. These advances have a non-negligible cost in terms of computation time and energy consumption. In this paper, we compare several learning strategies aiming at reducing such cost while keeping competitive performances. The experiments are performed on the MEDIA corpus, and show that it is possible to reduce the learning cost while maintaining state-of-the-art performances.
