Dataset Open Access
Olaf Jahn; Todor Ganchev; Marinez Isaac Marques; Karl-L. Schuchmann
Southern Lapwing Vanellus chilensis dataset accompanying the PLOS ONE article
O. Jahn, T. Ganchev, M.I. Marinez and K.L. Schuchmann: Automated Sound Recognition Provides Insights into the Behavioral Ecology of a Tropical Bird. DOI:10.1371/journal.pone.0169041
Background Library 01 consists of
BL01 >> BL_CHVACH_free_final:
54 hand-cleaned (Vanellus chilensis-free) background files and
BL01 >> PSC008_forest:
36 original soundscapes recorded inside forest, which may contain a few target signals from overflying lapwings.
Contains the Excel files
- 2013CHVACH_BreedingCycle_Statistics_PONE: statistics on V. chilensis activity patterns, Apr. 2013 to Sep. 2013.
- 2013CHVACH_FalseNegatives_PONE: determination of the false negative rate based on an expert-annotated sample of 26 soundcsape recordings
- 2013CHVACH_FalsePositives_PONE: determination of the false positive rate based on an expert-annotated random sample of 1250 automated V. chilensis detections.
Training library for the development of the V. chilensis recognizer, consisting of 90 hand-filtered recordings of the target species.
VACH_Detector_results >> VACHdetectorOutput_PONE.zip:
TXT detector output files, listing timestamps of potential V. chilensis sound events.
Validation library used to determine the false negative rate. The library consists of 26 expert-annotated sound files. Annotations were made in Adobe Audion v3.0.
Validation library used for the fine-tuning of the recognizer settings.
Important notes on the annotation of the VACH_FNrate_20160706 library:
1) In general, we used the procedure described in Ganchev et al. 2015 for the annotation of VACH validation libraries (see next section).
2) However, the detector-generated timestamps were not changed! For the following reasons, it is not possible to use the VACH_FN_rate library as a validation library for the development of improved recognizer versions:
(a) The VACH detector overlooked many of the weaker signals within a VACH call series. Therfore the detector-generated annotations are incomplete.
(b) For the same reason some automatically-generated detections may refer to a single VACH call event (double hits).
Details on the method used for the annotation of the VACH validation libraries are described in Ganchev et al. 2015, pp.6100f: 22.214.171.124.Vanellus chilensis validation dataset.