mlsanityData to 14 Oct 2026

Meta Auxiliary Learning for Low-resource Spoken Language Understanding

arXiv 2206.12774 ↗First posted 26 Jun 2022eess.AS cs.CL cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta auxiliary learning to improve the performance of low-resource SLU task by only taking advantage of abundant manual transcriptions of speech data. One obvious advantage of such method is that it provides a flexible framework to implement a low-resource SLU training task without requiring access to any further semantic annotations. In particular, a NLU model is taken as label generation network to predict intent and slot tags from texts; a multi-task network trains ASR task and SLU task synchronously from speech; and the predictions of label generation network are delivered to the multi-task network as semantic targets. The efficiency of the proposed algorithm is demonstrated with experiments on the public CATSLU dataset, which produces more suitable ASR hypotheses for the downstream NLU task.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 26 Jun 2022.

Builds on

25 of 30 references.

References · 25

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 193
  3. 2019Self-Supervised Generalisation with Meta Auxiliary Learningcited by 88
  4. 2020End-to-End Neural Transformer Based Spoken Language Understandingcited by 31
  5. 2019Meta Learning for End-to-End Low-Resource Speech Recognitioncited by 29
  6. 2020One Model, Many Languages: Meta-learning for Multilingual Text-to-Speechcited by 28
  7. 2019Using Speech Synthesis to Train End-to-End Spoken Language Understanding Modelscited by 24
  8. 2020Speech To Semantics: Improve ASR and NLU Jointly via All-Neural Interfacescited by 24
  9. 2020Meta-Transfer Learning for Code-Switched Speech Recognitioncited by 22
  10. 2020End-to-End Spoken Language Understanding Without Full Transcriptscited by 19
  11. 2020Improving End-to-End Speech-to-Intent Classification with Reptilecited by 17
  12. 2021End-to-End Spoken Language Understanding for Generalized Voice Assistantscited by 17
13 more
  1. 2020Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learningcited by 14
  2. 2020Large-scale Transfer Learning for Low-resource Spoken Language Understandingcited by 11
  3. 2021Integrating Dialog History into End-to-End Spoken Language Understanding Systemscited by 9
  4. 2020Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understandingcited by 8
  5. 2021Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputscited by 8
  6. 2021FANS: Fusing ASR and NLU for on-device SLUcited by 8
  7. 2021Sequential End-to-End Intent and Slot Label Classification and Localizationcited by 7
  8. 2021Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learningcited by 6
  9. 2021Representation based meta-learning for few-shot spoken intent recognitioncited by 5
  10. 2020End-to-end speech-to-dialog-act recognitioncited by 4
  11. 2019A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Datacited by 3
  12. 2020Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learningcited by 3
  13. 2022Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Modelcited by 3

Built on by

Not cited yet.