Designing efficient architectures for modeling temporal features with convolutional neural networks

@article{Pons2017DesigningEA,
  title={Designing efficient architectures for modeling temporal features with convolutional neural networks},
  author={J. Pons and X. Serra},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={2472-2476}
}
  • J. Pons, X. Serra
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Many researchers use convolutional neural networks with small rectangular filters for music (spectrograms) classification. First, we discuss why there is no reason to use this filters setup by default and second, we point that more efficient architectures could be implemented if the characteristics of the music features are considered during the design process. Specifically, we propose a novel design strategy that might promote more expressive and intuitive deep learning architectures by… CONTINUE READING
    43 Citations

    Tables and Topics from this paper.

    Timbre analysis of music audio signals with convolutional neural networks
    • 54
    • PDF
    DEEP LEARNING FOR MUSICAL INSTRUMENT RECOGNITION
    • Mingqing Yun
    • 2017
    Musical Tempo and Key Estimation using Convolutional Neural Networks with Directional Filters
    • 3
    • PDF
    Randomly Weighted CNNs for (Music) Audio Classification
    • J. Pons, X. Serra
    • Computer Science, Engineering
    • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2019
    • 35
    • PDF
    A Deep Neural Network for Audio Classification with a Classifier Attention Mechanism
    Investigating Kernel Shapes and Skip Connections for Deep Learning-Based Harmonic-Percussive Separation
    • 1
    • PDF
    Bottom-up Broadcast Neural Network For Music Genre Classification
    • 11
    • Highly Influenced
    • PDF
    End-to-end Learning for Music Audio Tagging at Scale
    • 70
    • PDF

    References

    SHOWING 1-10 OF 13 REFERENCES
    Experimenting with musically motivated convolutional neural networks
    • J. Pons, T. Lidy, X. Serra
    • Computer Science
    • 2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)
    • 2016
    • 88
    • PDF
    Improved musical onset detection with Convolutional Neural Networks
    • Jan Schlüter, S. Böck
    • Computer Science
    • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2014
    • 155
    • PDF
    Automatic Tagging Using Deep Convolutional Neural Networks
    • 179
    • PDF
    End-to-end learning for music audio
    • S. Dieleman, B. Schrauwen
    • Computer Science
    • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2014
    • 254
    • PDF
    Deep Convolutional Neural Networks for Predominant Instrument Recognition in Polyphonic Music
    • 95
    • PDF
    Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks
    • 79
    • Highly Influential
    • PDF
    Feature adapted convolutional neural networks for downbeat tracking
    • 15
    • Highly Influential
    • PDF
    Accurate Tempo Estimation Based on Recurrent Neural Networks and Resonating Comb Filters
    • 44
    • PDF
    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
    • 8,375
    • PDF
    Downbeat Tracking Using Beat Synchronous Features with Recurrent Neural Networks
    • 25
    • PDF