# Meta Auxiliary Learning for Low-resource Spoken Language Understanding

arXiv: https://arxiv.org/abs/2206.12774 · HTML: https://mlsanity.com/paper/2206.12774/

## 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 (most cited first, 25 of 25)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [End-to-End Neural Transformer Based Spoken Language Understanding](https://mlsanity.com/paper/2008.10984/) (2020)
- [Meta Learning for End-to-End Low-Resource Speech Recognition](https://mlsanity.com/paper/1910.12094/) (2019)
- [One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech](https://mlsanity.com/paper/2008.00768/) (2020)
- [Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models](https://mlsanity.com/paper/1910.09463/) (2019)
- [Speech To Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces](https://mlsanity.com/paper/2008.06173/) (2020)
- [Meta-Transfer Learning for Code-Switched Speech Recognition](https://mlsanity.com/paper/2004.14228/) (2020)
- [End-to-End Spoken Language Understanding Without Full Transcripts](https://mlsanity.com/paper/2009.14386/) (2020)
- [Improving End-to-End Speech-to-Intent Classification with Reptile](https://mlsanity.com/paper/2008.01994/) (2020)
- [End-to-End Spoken Language Understanding for Generalized Voice Assistants](https://mlsanity.com/paper/2106.09009/) (2021)
- [Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning](https://mlsanity.com/paper/2007.01836/) (2020)
- [Large-scale Transfer Learning for Low-resource Spoken Language Understanding](https://mlsanity.com/paper/2008.05671/) (2020)
- [Integrating Dialog History into End-to-End Spoken Language Understanding Systems](https://mlsanity.com/paper/2108.08405/) (2021)
- [Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding](https://mlsanity.com/paper/2005.11640/) (2020)
- [Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs](https://mlsanity.com/paper/2104.05752/) (2021)
- [FANS: Fusing ASR and NLU for on-device SLU](https://mlsanity.com/paper/2111.00400/) (2021)
- [Sequential End-to-End Intent and Slot Label Classification and Localization](https://mlsanity.com/paper/2106.04660/) (2021)
- [Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning](https://mlsanity.com/paper/2104.10357/) (2021)
- [Representation based meta-learning for few-shot spoken intent recognition](https://mlsanity.com/paper/2106.15238/) (2021)
- [End-to-end speech-to-dialog-act recognition](https://mlsanity.com/paper/2004.11419/) (2020)
- [A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data](https://mlsanity.com/paper/1904.04498/) (2019)
- [Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2005.11900/) (2020)
- [Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model](https://mlsanity.com/paper/2204.03315/) (2022)

## 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.