On the Potential of Simple Framewise Approaches to Piano Transcription

@inproceedings{Kelz2016OnTP,
  title={On the Potential of Simple Framewise Approaches to Piano Transcription},
  author={Rainer Kelz and Matthias Dorfer and Filip Korzeniowski and Sebastian B{\"o}ck and Andreas Arzt and Gerhard Widmer},
  booktitle={ISMIR},
  year={2016}
}
In an attempt at exploring the limitations of simple approaches to the task of piano transcription (as usually defined in MIR), we conduct an in-depth analysis of neural network-based framewise transcription. We systematically compare different popular input representations for transcription systems to determine the ones most suitable for use with neural networks. Exploiting recent advances in training techniques and new regularizers, and taking into account hyper-parameter tuning, we show that… CONTINUE READING
Highly Cited
This paper has 48 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 7 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 23 extracted citations

Automatic Music Transcription Leveraging Generalized Cepstral Features and Deep Learning

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 7 Excerpts
Highly Influenced

Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine Grained Audio Signal Labelling

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 6 Excerpts
Highly Influenced

Onsets and Frames: Dual-Objective Piano Transcription

ISMIR • 2018
View 7 Excerpts
Highly Influenced

Polyphonic Music Sequence Transduction with Meter-Constrained LSTM Networks

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 40 references

An End-to-End Neural Network for Polyphonic Piano Music Transcription

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2016
View 9 Excerpts
Highly Influenced

Adam: A Method for Stochastic Optimization

ICLR 2015 • 2015
View 4 Excerpts
Highly Influenced

Practical recommendations for gradient-based training of deep architectures

Neural Networks: Tricks of the Trade • 2012
View 3 Excerpts
Highly Influenced

LSTM: A Search Space Odyssey

IEEE Transactions on Neural Networks and Learning Systems • 2017
View 2 Excerpts

A hybrid recurrent neural network for music transcription

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 2 Excerpts

Lasagne: First release

Sander Dieleman, Jan Schlüter, +20 authors Jonas Degrave
2015
View 3 Excerpts