Audio Content based Geotagging in Multimedia

TL;DR

This paper introduces a novel approach to geotag multimedia recordings by analyzing their audio content, leveraging sound class composition and matrix factorization to infer location information.

Contribution

It presents a new method that uses audio-based semantic analysis and matrix factorization for geotagging multimedia recordings, which is a novel approach.

Findings

Effective identification of location from audio content.

Utilization of sound class composition for geotagging.

Application of matrix factorization techniques to audio data.

Abstract

In this paper we propose methods to extract geographically relevant information in a multimedia recording using its audio. Our method primarily is based on the fact that urban acoustic environment consists of a variety of sounds. Hence, location information can be inferred from the composition of sound events/classes present in the audio. More specifically, we adopt matrix factorization techniques to obtain semantic content of recording in terms of different sound classes. These semantic information are then combined to identify the location of recording.