Recent Advances In End-to-end Spoken Language Understanding

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.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keytomashenko2019recent

Related papers

• Where Are We In Semantic Concept Extraction For Spoken Language Understanding? (2021)5.84
• Speech-language Pre-training For End-to-end Spoken Language Understanding (2021)9.41
• End-to-end Architectures For Asr-free Spoken Language Understanding (2019)8.60
• Improving End-to-end Models For Set Prediction In Spoken Language Understanding (2022)0.00
• Towards End-to-end Spoken Language Understanding (2018)14.73
• Speech To Semantics: Improve ASR And NLU Jointly Via All-neural Interfaces (2020)9.03
• End-to-end Spoken Language Understanding For Generalized Voice Assistants (2021)6.34
• Understanding Semantics From Speech Through Pre-training (2019)0.00