Recent Advances in End-to-End Spoken Language Understanding

September 29, 2019 · The Cartographer · 🏛 International Conference on Statistical Language and Speech Processing

"No code URL or promise found in abstract"
"Title-pattern auto-detect: Recent Advances in End-to-End Spoken Language Understanding"

Evidence collected by the PWNC Scanner

Authors Natalia Tomashenko, Antoine Caubriere, Yannick Esteve, Antoine Laurent, Emmanuel Morin arXiv ID 1909.13332 Category cs.CL: Computation & Language Cross-listed eess.AS Citations 29 Venue International Conference on Statistical Language and Speech Processing Last Checked 2 days ago

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.