Stacked convolutional and recurrent neural networks for bird audio detection

@article{Adavanne2017StackedCA,
  title={Stacked convolutional and recurrent neural networks for bird audio detection},
  author={Sharath Adavanne and Konstantinos Drossos and Emre Çakir and Tuomas Virtanen},
  journal={2017 25th European Signal Processing Conference (EUSIPCO)},
  year={2017},
  pages={1729-1733}
}
This paper studies the detection of bird calls in audio segments using stacked convolutional and recurrent neural networks. Data augmentation by blocks mixing and domain adaptation using a novel method of test mixing are proposed and evaluated in regard to making the method robust to unseen data. The contributions of two kinds of acoustic features (dominant frequency and log mel-band energy) and their combinations are studied in the context of bird audio detection. Our best achieved AUC measure… Expand
39 Citations
Convolutional recurrent neural networks for bird audio detection
3D convolution recurrent neural networks for bird sound detection
Acoustic Scene Classification Using Spatial Pyramid Pooling with Convolutional Neural Networks
Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network
Deep Multiple Instance Learning Ensemble for the Acoustic Detection of Tropical Birds
Raw Waveform-based Audio Classification Using Sample-level CNN Architectures
...
1
2
3
4
...

References

SHOWING 1-10 OF 30 REFERENCES
Convolutional recurrent neural networks for bird audio detection
Sound event detection using spatial features and convolutional recurrent neural network
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
Convolutional recurrent neural networks for music classification
Recurrent neural networks for polyphonic sound event detection in real life recordings
Bird species recognition combining acoustic and sequence modeling
Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks
Bird detection in audio: A survey and a challenge
Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning
Acoustics and physical models of bird sounds
...
1
2
3
...