Audio onset detection: A wavelet packet based approach with recurrent neural networks

@article{Marchi2014AudioOD,
  title={Audio onset detection: A wavelet packet based approach with recurrent neural networks},
  author={Erik Marchi and Giacomo Ferroni and Florian Eyben and Stefano Squartini and Bj{\"o}rn W. Schuller},
  journal={2014 International Joint Conference on Neural Networks (IJCNN)},
  year={2014},
  pages={3585-3591}
}

• Erik Marchi, Giacomo Ferroni, +2 authors Björn W. Schuller
• Published 2014 in
  2014 International Joint Conference on Neural…
• DOI:10.1109/IJCNN.2014.6889669

This paper concerns the exploitation of multi-resolution time-frequency features via Wavelet Packet Transform to improve audio onset detection. In our approach, Wavelet Packet Energy Coefficients (WPEC) and Auditory Spectral Features (ASF) are processed by Bidirectional Long Short-Term Memory (BLSTM) recurrent neural network that yields the onsets location. The combination of the two feature sets, together with the BLSTM based detector, form an advanced energy-based approach that takes… CONTINUE READING

Save to Library

Create Alert

Cite

View on IEEE