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.

Authors: Kelz, Rainer; Widmer, Gerhard
Affiliation: Johannes Kepler University, Linz, Austria
AES Conference: 2017 AES International Conference on Semantic Audio (June 2017)
Paper Number: 5-1
Publication Date: June 13, 2017 Import into BibTeX
Subject: Deep Learning
Permalink: http://www.aes.org/e-lib/browse.cfm?elib=18761

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:   /conf/2017/semantic/semantic_audio_2017_paper_18.pdf

Start a discussion about this paper!