ASGIR: Audio Spectrogram Transformer Guided Classification And Information Retrieval For Birds

TL;DR

ASGIR is a novel audio spectrogram transformer framework that significantly improves bird sound recognition and enables efficient information retrieval using geographical and sound data, achieving near-perfect accuracy on a European bird dataset.

Contribution

The paper introduces ASGIR, a new spectrogram transformer-based framework for bird sound classification and a two-step retrieval system integrating geographical data and Wikipedia scraping.

Findings

Achieved median 100% F1, Precision, and Sensitivity on a 51-class bird dataset.

Demonstrated effective integration of sound and location data for bird information retrieval.

Provided an accessible implementation for ecological and ornithological research.

Abstract

Recognition and interpretation of bird vocalizations are pivotal in ornithological research and ecological conservation efforts due to their significance in understanding avian behaviour, performing habitat assessment and judging ecological health. This paper presents an audio spectrogram-guided classification framework called ASGIR for improved bird sound recognition and information retrieval. Our work is accompanied by a simple-to-use, two-step information retrieval system that uses geographical location and bird sounds to localize and retrieve relevant bird information by scraping Wikipedia page information of recognized birds. ASGIR offers a substantial performance on a random subset of 51 classes of Xeno-Canto dataset Bird sounds from European countries with a median of 100\% performance on F1, Precision and Sensitivity metrics. Our code is available as follows: https://github.com/MainSample1234/AS-GIR .