An evaluation of data augmentation methods for sound scene geotagging
This work addresses the need for more accurate audio-based location identification, which is useful for applications like audio surveillance, but it is incremental as it builds on existing methods.
The paper tackled the problem of sound scene geotagging by evaluating common audio data augmentation methods to improve classifier accuracy, resulting in a 23% improvement over the state-of-the-art city geotagging method.
Sound scene geotagging is a new topic of research which has evolved from acoustic scene classification. It is motivated by the idea of audio surveillance. Not content with only describing a scene in a recording, a machine which can locate where the recording was captured would be of use to many. In this paper we explore a series of common audio data augmentation methods to evaluate which best improves the accuracy of audio geotagging classifiers. Our work improves on the state-of-the-art city geotagging method by 23% in terms of classification accuracy.