DB3V: A Dialect Dominated Dataset of Bird Vocalisation for Cross-corpus Bird Species Recognition

TL;DR

This paper introduces DB3V, a comprehensive dataset of bird vocalisations emphasizing dialect differences across regions, and provides baseline models for cross-corpus bird species recognition to advance research in this area.

Contribution

It presents the first cross-corpus bird vocalisation dataset focused on dialects, enabling improved benchmarking and understanding of dialect impacts on species recognition.

Findings

DB3V contains over 25 hours of recordings from 10 species across three regions.

Baseline models demonstrate challenges in cross-corpus bird recognition due to dialect variations.

The dataset facilitates future research on dialect-aware bird species identification.

Abstract

In ornithology, bird species are known to have variedit's widely acknowledged that bird species display diverse dialects in their calls across different regions. Consequently, computational methods to identify bird species onsolely through their calls face critsignificalnt challenges. There is growing interest in understanding the impact of species-specific dialects on the effectiveness of bird species recognition methods. Despite potential mitigation through the expansion of dialect datasets, the absence of publicly available testing data currently impedes robust benchmarking efforts. This paper presents the Dialect Dominated Dataset of Bird Vocalisation, the first cross-corpus dataset that focuses on dialects in bird vocalisations. The DB3V comprises more than 25 hours of audio recordings from 10 bird species distributed across three distinct regions in the contiguous United States (CONUS). In addition to presenting the dataset, we conduct analyses and establish baseline models for cross-corpus bird recognition. The data and code are publicly available online: https://zenodo.org/records/11544734