# Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance

arXiv: https://arxiv.org/abs/2308.04886 · HTML: https://mlsanity.com/paper/2308.04886/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 9 Aug 2023.

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

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Pretrained Transformers Improve Out-of-Distribution Robustness](https://mlsanity.com/paper/2004.06100/) (2020)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [DOC: Deep Open Classification of Text Documents](https://mlsanity.com/paper/1709.08716/) (2017)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure](https://mlsanity.com/paper/2101.00387/) (2021)
- [Unsupervised Out-of-Domain Detection via Pre-trained Transformers](https://mlsanity.com/paper/2106.00948/) (2021)
- [AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition](https://mlsanity.com/paper/2005.07973/) (2020)
- [Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings](https://mlsanity.com/paper/2110.03520/) (2021)
- [Finnish Dialect Identification: The Effect of Audio and Text](https://mlsanity.com/paper/2111.03800/) (2021)
- [Transformer-based Arabic Dialect Identification](https://mlsanity.com/paper/2011.00699/) (2020)
- [Dynamic Multi-scale Convolution for Dialect Identification](https://mlsanity.com/paper/2108.07787/) (2021)

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

- [Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification](https://mlsanity.com/paper/2406.18067/) (2024)

## Abstract (arXiv)

Dialect classification is used in a variety of applications, such as machine translation and speech recognition, to improve the overall performance of the system. In a real-world scenario, a deployed dialect classification model can encounter anomalous inputs that differ from the training data distribution, also called out-of-distribution (OOD) samples. Those OOD samples can lead to unexpected outputs, as dialects of those samples are unseen during model training. Out-of-distribution detection is a new research area that has received little attention in the context of dialect classification. Towards this, we proposed a simple yet effective unsupervised Mahalanobis distance feature-based method to detect out-of-distribution samples. We utilize the latent embeddings from all intermediate layers of a wav2vec 2.0 transformer-based dialect classifier model for multi-task learning. Our proposed approach outperforms other state-of-the-art OOD detection methods significantly.