An Experimental Analysis of the Entanglement Problem in Neural-Network-based Music Transcription Systems
Abstract
Several recent polyphonic music transcription systems have utilized deep neural networks to achieve state of the art results on various benchmark datasets, pushing the envelope on framewise and note-level performance measures. Unfortunately we can observe a sort of glass ceiling effect. To investigate this effect, we provide a detailed analysis of the particular kinds of errors that state of the art deep neural transcription systems make, when trained and tested on a piano transcription task. We are ultimately forced to draw a rather disheartening conclusion: the networks seem to learn combinations of notes, and have a hard time generalizing to unseen combinations of notes. Furthermore, we speculate on various means to alleviate this situation.
Keywords
Cite
@article{arxiv.1702.00025,
title = {An Experimental Analysis of the Entanglement Problem in Neural-Network-based Music Transcription Systems},
author = {Rainer Kelz and Gerhard Widmer},
journal= {arXiv preprint arXiv:1702.00025},
year = {2017}
}
Comments
Submitted to AES Conference on Semantic Audio, Erlangen, Germany, 2017 June 22, 24