Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance. (arXiv:2308.04886v1 [cs.CL])

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 …

applications arxiv classification classification model data detection distribution machine machine translation performance recognition speech speech recognition training training data translation unsupervised world