Wu, Guan WeiGuan WeiWuLin, Guan TingGuan TingLinLi, Shang WenShang WenLiHUNG-YI LEE2023-10-192023-10-192023-01-012308457Xhttps://scholars.lib.ntu.edu.tw/handle/123456789/636198Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech Recognition (ASR) models or paired text as intermediate targets. However, acquiring paired transcripts is expensive and impractical for unwritten languages. On the other hand, Textless SLU extracts semantic information from speech without utilizing paired transcripts. However, the absence of intermediate targets and training guidance for textless SLU often leads to suboptimal performance. In this work, inspired by the content-disentangled discrete units from self-supervised speech models, we proposed to use discrete units as intermediate guidance to improve textless SLU performance. Our method surpasses the baseline method on five SLU benchmark corpora. Additionally, we find that unit guidance facilitates few-shot learning and enhances noise robustness.Self-Supervised Learning | Spoken Language Understanding | Textless NLP[SDGs]SDG4conference paper10.21437/Interspeech.2023-17182-s2.0-85171558050https://api.elsevier.com/content/abstract/scopus_id/85171558050