Label Tree Embeddings for Acoustic Scene Classification
This work addresses acoustic scene classification, a domain-specific problem, with incremental improvements.
The paper tackles acoustic scene classification by learning a category taxonomy from class labels and embedding instances into low-dimensional features based on meta-class likelihoods, achieving state-of-the-art results on the DCASE 2013 and LITIS Rouen datasets.
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.