Machine Learning of Personal Gesture Variation in Music Conducting

Sarasua, Alvaro; Caramiaux, Baptiste and Tanaka, Atau. 2016. 'Machine Learning of Personal Gesture Variation in Music Conducting'. In: UNSPECIFIED. UNDEFINED. [Conference or Workshop Item]

[img]
Preview
Text
pn1447-sarasuaA.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (357kB) | Preview
[img]
Preview
Video (Demo: Machine Learning of Expressive Gestures)
file1447-1.mp4 - Supplemental Material
Available under License Creative Commons Attribution No Derivatives.

Download (11MB) | Preview
[img] Video (YouTube: ACM SIGCHI 2016 presentation)
maxresdefault.jpg - Presentation

Download (0B)
[img] Video
ERROR: ylqTxJiYfTg: "token" parameter not in video info for unknown reason; please report this issue on https://yt-dl.org/bug . Make sure you are using the latest version; type youtube-dl -U to update. Be sure to call youtube-dl with the --verbose flag

Download (0B)

Abstract or Description

This note presents a system that learns expressive and id- iosyncratic gesture variations for gesture-based interaction. The system is used as an interaction technique in a music con- ducting scenario where gesture variations drive music articu- lation. A simple model based on Gaussian Mixture Modeling is used to allow the user to configure the system by provid- ing variation examples. The system performance and the in- fluence of user musical expertise is evaluated in a user study, which shows that the model is able to learn idiosyncratic vari- ations that allow users to control articulation, with better per- formance for users with musical expertise.

Item Type:

Conference or Workshop Item (UNSPECIFIED)

Identification Number (DOI):

https://doi.org/10.1145/2858036.2858328

Keywords:

SIGCHI, CHI 2016, music interfaces, Human computer interaction (HCI), expressive interaction, music conducting, Machine learning approaches, gesture-based in...

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
May 2016Published
8 January 2016Accepted

Item ID:

17510

Date Deposited:

23 Mar 2016 08:46

Last Modified:

10 Jun 2021 05:03

URI:

https://research.gold.ac.uk/id/eprint/17510

View statistics for this item...

Edit Record Edit Record (login required)