# Out-of-distribution generalisation in spoken language understanding

arXiv: https://arxiv.org/abs/2407.07425 · HTML: https://mlsanity.com/paper/2407.07425/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [What Algorithms can Transformers Learn? A Study in Length Generalization](https://mlsanity.com/paper/2310.16028/) (2023)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Towards end-to-end spoken language understanding](https://mlsanity.com/paper/1802.08395/) (2018)
- [From Audio to Semantics: Approaches to end-to-end spoken language understanding](https://mlsanity.com/paper/1809.09190/) (2018)
- [Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization](https://mlsanity.com/paper/1907.04371/) (2019)
- [Break It Down: Evidence for Structural Compositionality in Neural Networks](https://mlsanity.com/paper/2301.10884/) (2023)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [Structural generalization is hard for sequence-to-sequence models](https://mlsanity.com/paper/2210.13050/) (2022)
- [End-to-end architectures for ASR-free spoken language understanding](https://mlsanity.com/paper/1910.10599/) (2019)
- [Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding](https://mlsanity.com/paper/2106.15065/) (2021)
- [Monotonic Location Attention for Length Generalization](https://mlsanity.com/paper/2305.20019/) (2023)
- [Compositional Generalization in Spoken Language Understanding](https://mlsanity.com/paper/2312.15815/) (2023)

## Built on by (most cited first, 1 of 1)

- [Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shifts](https://mlsanity.com/paper/2507.23128/) (2025)

## Abstract (arXiv)

Test data is said to be out-of-distribution (OOD) when it unexpectedly differs from the training data, a common challenge in real-world use cases of machine learning. Although OOD generalisation has gained interest in recent years, few works have focused on OOD generalisation in spoken language understanding (SLU) tasks. To facilitate research on this topic, we introduce a modified version of the popular SLU dataset SLURP, featuring data splits for testing OOD generalisation in the SLU task. We call our modified dataset SLURP For OOD generalisation, or SLURPFOOD. Utilising our OOD data splits, we find end-to-end SLU models to have limited capacity for generalisation. Furthermore, by employing model interpretability techniques, we shed light on the factors contributing to the generalisation difficulties of the models. To improve the generalisation, we experiment with two techniques, which improve the results on some, but not all the splits, emphasising the need for new techniques.