Label Tree Embeddings for Acoustic Scene Classification. (arXiv:1606.07908v2 [cs.MM] UPDATED)

We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering of the labels into multiple meta-classes in a tree structure. An acoustic scene instance is then embedded into a low-dimensional feature representation which consists of the likelihoods that it belongs to the meta-classes. We demonstrate state-of-the-art results on two different datasets for the acoustic scene classification task, including the DCASE 2013 and LITIS Rouen datasets.

from cs.AI updates on arXiv.org http://ift.tt/28ZsKDL
via IFTTT