Improved onset detection for traditional flute recordings using convolutional neural networks

Hockman, Jason and Ali-MacLachlan, Islah and Tomczak, Maciej and Southall, Carl (2017) Improved onset detection for traditional flute recordings using convolutional neural networks. In: The 7th International Workshop on Folk Music Analysis. (In Press)

[img]
Preview
Text
Hockman - improved onset.pdf - Accepted Version

Download (361kB)

Abstract

The usage of ornaments is key attribute that defines the style of
a flute performances within the genre of Irish Traditional Music
(ITM). Automated analysis of ornaments in ITM would allow for
the musicological investigation of a player’s style and would be
a useful feature in the analysis of trends within large corpora of
ITM music. As ornament onsets are short and subtle variations
within an analysed signal, they are substantially more difficult to
detect than longer notes. This paper addresses the topic of onset
detection for notes, ornaments and breaths in ITM. We propose
a new onset detection method based on a convolutional neural
network (CNN) trained solely on flute recordings of ITM. The
presented method is evaluated alongside a state-of-the-art gen-
eralised onset detection method using a corpus of 79 full-length
solo flute recordings. The results demonstrate that the proposed
system outperforms the generalised system over a range of musi-
cal patterns idiomatic of the genre.

Item Type: Conference or Workshop Item (Paper)
Subjects: G400 Computer Science
Divisions: Faculty of Computing, Engineering and the Built Environment
Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology
Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology > Digital Media Technology
UoA Collections > UoA11: Computer Science and Informatics
Depositing User: Oana-Andreea Dumitrascu
Date Deposited: 28 Jun 2017 08:48
Last Modified: 10 Oct 2017 14:11
URI: http://www.open-access.bcu.ac.uk/id/eprint/4748

Actions (login required)

View Item View Item

Research

In this section...