End-to-end spoken language understanding using transformer networks and self-supervised pre-trained features

Autor:	Morais, Edmilson, Kuo, Hong-Kwang J., Thomas, Samuel, Tuske, Zoltan, Kingsbury, Brian
Rok vydání:	2020
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Transformer networks and self-supervised pre-training have consistently delivered state-of-art results in the field of natural language processing (NLP); however, their merits in the field of spoken language understanding (SLU) still need further investigation. In this paper we introduce a modular End-to-End (E2E) SLU transformer network based architecture which allows the use of self-supervised pre-trained acoustic features, pre-trained model initialization and multi-task training. Several SLU experiments for predicting intent and entity labels/values using the ATIS dataset are performed. These experiments investigate the interaction of pre-trained model initialization and multi-task training with either traditional filterbank or self-supervised pre-trained acoustic features. Results show not only that self-supervised pre-trained acoustic features outperform filterbank features in almost all the experiments, but also that when these features are used in combination with multi-task training, they almost eliminate the necessity of pre-trained model initialization. Comment: 5 pages, 3 tables and 1 figure
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2011.08238 Zobrazit plný text záznamu View this record from Arxiv