Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929286851592192 |
|---|---|
| author | Das, Sourya Dipta Vadi, Yash Unnam, Abhishek Yadav, Kuldeep |
| author_facet | Das, Sourya Dipta Vadi, Yash Unnam, Abhishek Yadav, Kuldeep |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_04886 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance Das, Sourya Dipta Vadi, Yash Unnam, Abhishek Yadav, Kuldeep Computation and Language Computer Vision and Pattern Recognition Sound Audio and Speech Processing 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. |
| title | Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance |
| topic | Computation and Language Computer Vision and Pattern Recognition Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2308.04886 |