Skip to Main content Skip to Navigation
Conference papers

Densely Connected CNNs for Bird Audio Detection

Abstract : Detecting bird sounds in audio recordings automatically, if accurate enough, is expected to be of great help to the research community working in bio- and ecoacoustics, interested in monitoring biodiversity based on audio field recordings. To estimate how accurate the state-of-the-art machine learning approaches are, the Bird Audio Detection challenge involving large audio datasets was recently organized. In this paper, experiments using several types of convolutional neural networks (i.e. standard CNNs, residual nets and densely connected nets) are reported in the framework of this challenge. DenseNets were the preferred solution since they were the best performing and most compact models, leading to a 88.22% area under the receiver operator curve score on the test set of the challenge. Performance gains were obtained thank to data augmentation through time and frequency shifting, model parameter averaging during training and ensemble methods using the geometric mean. On the contrary, the attempts to enlarge the training dataset with samples of the test set with automatic predictions used as pseudo-groundtruth labels consistently degraded performance.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01913975
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Tuesday, November 6, 2018 - 4:15:52 PM
Last modification on : Monday, June 15, 2020 - 3:35:36 AM
Document(s) archivé(s) le : Thursday, February 7, 2019 - 4:11:08 PM

File

pellegrini_19111.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01913975, version 1
  • OATAO : 19111

Citation

Thomas Pellegrini. Densely Connected CNNs for Bird Audio Detection. 25th European Signal and Image Processing Conference (EUSIPCO 2017), Aug 2017, Kos island, Greece. pp. 1734-1738. ⟨hal-01913975⟩

Share

Metrics

Record views

75

Files downloads

222