Logo
Logo

Goldsmiths - University of London

Using Interactive Machine Learning to Support Interface Development Through Workshops with Disabled People

Katan, Simon; Grierson, Mick and Fiebrink, Rebecca. 2015. 'Using Interactive Machine Learning to Support Interface Development Through Workshops with Disabled People'. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI '15). Seoul, Korea, Republic of 18-23 April 2015. [Conference or Workshop Item]

[img]
Preview
Text
KatanGriersonFiebrink_CHI2015.pdf - Accepted Version

Download (502kB) | Preview

Abstract or Description

We have applied interactive machine learning (IML) to the creation and customisation of gesturally controlled musical interfaces in six workshops with people with learning and physical disabilities. Our observations and discussions with participants demonstrate the utility of IML as a tool for participatory design of accessible interfaces. This work has also led to a better understanding of challenges in end-user training of learning models, of how people develop personalised interaction strategies with different types of pre-trained interfaces, and of how properties of control spaces and input devices influence people’s customisation strategies and engagement with instruments. This work has also uncovered similarities between the musical goals and practices of disabled people and those of expert musicians.

Item Type: Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1145/2702123.2702474

Keywords:

Interactive machine learning; accessible interfaces; music.

Departments, Centres and Research Units:

Computing
Computing > Embodied AudioVisual Interaction Group (EAVI)

Dates:

DateEvent
18 April 2015Published

Event Location:

Seoul, Korea, Republic of

Date range:

18-23 April 2015

Item ID:

17347

Date Deposited:

22 Mar 2016 09:05

Last Modified:

20 Jun 2017 10:35

URI: http://research.gold.ac.uk/id/eprint/17347

View statistics for this item...

Edit Record Edit Record (login required)