Recent Advances in End-to-End Spoken Language Understanding

TL;DR

This paper reviews recent progress in end-to-end spoken language understanding, focusing on neural models for extracting semantic info directly from speech for NER and slot filling tasks, using techniques like speaker adaptation and pretraining.

Contribution

It introduces novel methods and training strategies to enhance end-to-end SLU performance for NER and slot filling tasks.

Findings

Improved accuracy with speaker adaptation techniques

Enhanced model performance through modified CTC training

Effective use of sequential pretraining for SLU tasks

Abstract

This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are considered: named entity recognition (NER) and semantic slot filling (SF). For these tasks, in order to improve the model performance, we explore various techniques including speaker adaptation, a modification of the connectionist temporal classification (CTC) training criterion, and sequential pretraining.