End-to-end Architectures For Asr-free Spoken Language Understanding

Abstract

Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text, followed by a Natural Language Understanding (NLU) model to extract meaning from the decoded text. Recently, end-to-end approaches were emerged, aiming at unifying the ASR and NLU into a single SLU deep neural architecture, trained using combinations of ASR and NLU-level recognition units. In this paper, we explore a set of recurrent architectures for intent classification, tailored to the recently introduced Fluent Speech Commands (FSC) dataset, where intents are formed as combinations of three slots (action, object, and location). We show that by combining deep recurrent architectures with standard data augmentation, state-of-the-art results can be attained, without using ASR-level targets or pretrained ASR models. We also investigate its generali

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keypalogiannidi2019end

Related papers

• Speech To Semantics: Improve ASR And NLU Jointly Via All-neural Interfaces (2020)9.03
• Recent Advances In End-to-end Spoken Language Understanding (2019)8.09
• RNN Based Incremental Online Spoken Language Understanding (2019)0.00
• Speech-language Pre-training For End-to-end Spoken Language Understanding (2021)9.41
• End-to-end Spoken Language Understanding For Generalized Voice Assistants (2021)6.34
• End-to-end Spoken Language Understanding: Performance Analyses Of A Voice Command Task In A Low Resource Setting (2022)8.35
• Integrating Pretrained ASR And LM To Perform Sequence Generation For Spoken Language Understanding (2023)5.24
• Where Are We In Semantic Concept Extraction For Spoken Language Understanding? (2021)5.84