An intent classification system is usually implemented as a pipeline process, with aspeech recognition module followed by text processing that classifies theintents . Such systems don’t take advantage of relevant linguistic information, and suffer from limited training data . In this work, we propose a novel intent classification framework that uses acoustic features extracted from a speech recognition system and linguistic features learned from a pretrained language model . With the proposed method, we achieve 90.86% and 99.07% accuracy on ATIS and Fluentspeech corpus, respectively. We achieve the method with theproposed method, which is based on a combination of both acoustic and linguisticembeddings .

Author(s) : Bidisha Sharma, Maulik Madhavi, Haizhou Li

Links : PDF - Abstract

Code :

Keywords : acoustic - classification - intent - linguistic - method -

Leave a Reply

Your email address will not be published. Required fields are marked *