Large-scale Identification of Birds in Audio Recordings

@inproceedings{Lasseck2014LargescaleIO,
  title={Large-scale Identification of Birds in Audio Recordings},
  author={Mario Lasseck},
  booktitle={CLEF},
  year={2014}
}
The Bird Identification Task of the LifeCLEF 2014 lab is to automatically identify 501 different species in over 4000 audio recordings collected by amateur and expert ornithologists through a citizen sciences initiative. It is one of the biggest bird classification challenges so far considering the quality, quantity and variability of the recordings and the very large number of different species to be classified. The solution presented here achieves a Mean Average Precision of 51.1% on the test… CONTINUE READING
BETA

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • The solution presented here achieves a Mean Average Precision of 51.1% on the test set and 53.9% on the training set with an Area Under the Curve of 91.5% during cross-validation.

Citations

Publications citing this paper.
SHOWING 1-10 OF 27 CITATIONS

Deductive refinement of species labelling in weakly labelled birdsong recordings

  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Bird Sound Classification Individual Project

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Deep learning for detection of bird vocalisations

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

LifeCLEF 2014: Multimedia Life Species Identification Challenges

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…