Skip to main content
zenodoopen

Birdsong NOIZEUS: Bioacoustics noise reduction benchmark dataset

<p>------------------------------------------------------------------------<br>Birdsong noizeus dataset<br>------------------------------------------------------------------------</p> <p>Authors: Tim Sainburg &amp; Asaf Zorea<br>Year: 2024</p> <p>------------------------------------------------------------------------<br>General information<br>------------------------------------------------------------------------<br>- There are 5 recordings from each of 14 individuals (European starlings) recorded in an acoustically isolated chamber.&nbsp;<br>- For each song, we apply noise at 5 SNR levels (0dB, 5dB, 10dB, 15dB).&nbsp;<br>- There are 8 noise types, each taken from a single noise clip from the "Soundscapes from around the world" dataset.<br>- They are "rain", "town", "wind", "waterfall", "insect", "swamp" "frogscape", "forest"<br>- Each soundscape contains multiple noise sources.&nbsp;<br>- Noise levels were estimated using the pyloudnorm software (Steinmetz et al., 2021)<br>- Audio is provided as waveforms at 44100 samplerate</p> <p>------------------------------------------------------------------------<br>Data format<br>------------------------------------------------------------------------</p> <p>- clean<br>&nbsp; &nbsp; - {bird_name}_{timestamp}.wav<br>- noisy<br>&nbsp; &nbsp; - {snr}dB<br>&nbsp; &nbsp; &nbsp; &nbsp; - {bird_name}_{timestamp}_{noise_category}_{snr}.wav<br>- noise_sample<br>&nbsp; &nbsp; - {snr}dB<br>&nbsp; &nbsp; &nbsp; &nbsp; - {bird_name}_{timestamp}_{noise_category}_{snr}.wav</p> <p>`clean` contains the original clean audio.<br>`noisy` contains the song+noise<br>`noise_sample` contains a 1-second sample of noise only.&nbsp;</p> <p>Timestamp is in the format YYYY-MM-DD_HH-MM-SS-MILLISECONDS and refers to the time that the song was recorded.&nbsp;</p> <p>------------------------------------------------------------------------<br>Data sources<br>------------------------------------------------------------------------</p> <p>Birdsong<br>---------<br>Birdsong are acoustically isolated songs from 14 European Starlings<br>https://zenodo.org/records/3237218</p> <p>Citation:&nbsp;<br>Arneodo, Z., Sainburg, T., Jeanne, J., &amp; Gentner, T. (2019). An acoustically isolated European starling song library (Version v1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.3237218</p> <p>This dataset is available under the following license:<br>- &nbsp;Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/legalcode)</p> <p><br>Noise<br>-----<br>Noise are taken from the Xeno-canto - "Soundscapes from around the world" dataset<br>https://www.gbif.org/dataset/ff571aeb-46bf-45c4-ad2c-af4d68315765</p> <p>Citation:<br>Vellinga W (2024). Xeno-canto - Soundscapes from around the world. Xeno-canto Foundation for Nature Sounds. Occurrence dataset https://doi.org/10.15468/9u3zaq accessed via GBIF.org on 2024-10-17.</p> <p>We sampled 8 soundscapes from this dataset:<br>&nbsp; &nbsp; 1. Rain https://www.gbif.org/occurrence/4523646364<br>&nbsp; &nbsp; &nbsp; &nbsp; - Virginia<br>&nbsp; &nbsp; &nbsp; &nbsp; - 457s<br>&nbsp; &nbsp; &nbsp; &nbsp; - rain, Recording of the feeders in the backyard with a light rain falling on the leaf litter, while a freight train passes by ~1/2 mile away.<br>&nbsp; &nbsp; 2. Town https://xeno-canto.org/696263<br>&nbsp; &nbsp; &nbsp; &nbsp; - 2:22<br>&nbsp; &nbsp; &nbsp; &nbsp; - &nbsp;the closer habitat are greater trees and coniferes ..smaller bushes ...some other Krautg&auml;rten ... traffic-noise is to hear..as airplanes,too.<br>&nbsp; &nbsp; &nbsp; &nbsp; - insects, birds, bells, traffic?, airplane<br>&nbsp; &nbsp; &nbsp; &nbsp; - Germany<br>&nbsp; &nbsp; 3. Wind https://xeno-canto.org/911773<br>&nbsp; &nbsp; &nbsp; &nbsp; - 5:29<br>&nbsp; &nbsp; &nbsp; &nbsp; - Very windy day, grassland to shrubland habitat<br>&nbsp; &nbsp; &nbsp; &nbsp; - Wisconsin<br>&nbsp; &nbsp; 4. Waterfall https://xeno-canto.org/406993<br>&nbsp; &nbsp; &nbsp; &nbsp; - 24:02<br>&nbsp; &nbsp; &nbsp; &nbsp; - sound scenes captured in a river forest with zarzas, hiedras and other matorrales at the edge of a small waterfall.<br>&nbsp; &nbsp; &nbsp; &nbsp; - Spain<br>&nbsp; &nbsp; 5. Insect https://xeno-canto.org/454914<br>&nbsp; &nbsp; &nbsp; &nbsp; - 5:45<br>&nbsp; &nbsp; &nbsp; &nbsp; - Australia<br>&nbsp; &nbsp; &nbsp; &nbsp; - cicadias, birds,<br>&nbsp; &nbsp; 6. Swanp https://xeno-canto.org/909875<br>&nbsp; &nbsp; &nbsp; &nbsp; - 2:24<br>&nbsp; &nbsp; &nbsp; &nbsp; - Swampy area along dirt road/trail. Species Include: American Bullfrog, Cricket Frogs, American Crow, Prothonotary Warbler, Red-winged Blackbird, Indigo Bunting, Northern Cardinal<br>&nbsp; &nbsp; 7. Frogscape https://xeno-canto.org/718213<br>&nbsp; &nbsp; &nbsp; &nbsp; - 4:42&nbsp;<br>&nbsp; &nbsp; &nbsp; &nbsp; - European Tree Frog Hyla arborea Green Frog Pelophlyax sp.<br>&nbsp; &nbsp; &nbsp; &nbsp; - Austrial&nbsp;<br>&nbsp; &nbsp; 8. Forest https://xeno-canto.org/900744&nbsp;<br>&nbsp; &nbsp; &nbsp; &nbsp; - 3:04<br>&nbsp; &nbsp; &nbsp; &nbsp; - Sweden<br>&nbsp; &nbsp; &nbsp; &nbsp; - A beautiful choir with frogs, toads, geese and ducks to enjoy in the darkness a foggy night.<br>&nbsp; &nbsp; &nbsp; &nbsp;&nbsp;<br>&nbsp; &nbsp; &nbsp; &nbsp;&nbsp;<br>&nbsp; &nbsp; &nbsp; &nbsp;&nbsp;<br>All noise recordings have one of the following licensesL<br>- Creative Commons Attribution-NonCommercial-ShareAlike 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)<br>- Creative Commons Attribution-ShareAlike 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)</p> <p><br>Additional information about the noise dataset</p> <p><br>------------------------------------------------------------------------<br>citations<br>------------------------------------------------------------------------</p> <p>Steinmetz, C. J., &amp; Reiss, J. (2021, May). pyloudnorm: A simple yet flexible loudness meter in python. In Audio Engineering Society Convention 150. Audio Engineering Society.</p> <p>Arneodo, Z., Sainburg, T., Jeanne, J., &amp; Gentner, T. (2019). An acoustically isolated European starling song library (Version v1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.3237218</p> <p>Vellinga W (2024). Xeno-canto - Soundscapes from around the world. Xeno-canto Foundation for Nature Sounds. Occurrence dataset https://doi.org/10.15468/9u3zaq accessed via GBIF.org on 2024-10-17.</p>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
8
Access
12
Reuse readiness
8
Engagement
4

Topics