Sonification Examples for:
Relevance-based Interactive Optimization of Sonifications
Authors: Thomas Hermann, Kerstin Bunte, Helge Ritter
Conference: International
Conference on Auditory Display (ICAD 2007), Montreal, Canada,
June, 2007
Abstract
This paper presents a novel approach for the interactive optimization
of sonification parameters. In a closed loop, the system automatically
generates modified versions of an initial (or previously selected)
sonification via gradient ascend or evolutionary algorithms. The human
listener directs the optimization process by providing relevance
feedback about the perceptual quality of these propositions.
In summary, the scheme allows users to bring in their perceptual
capabilities without burdening them with computational tasks. It also
allows for continuous update of exploration goals in the course of an
exploration task. Finally, Interactive Optimization is a promising
novel paradigm for solving the mapping problems and for a user-centred
design of auditory display. The paper gives a full account on the
technique, and demonstrates the optimization at hand of synthetic and
real-world data sets.
Article Link: HermannBunteRitter2007-RBI.pdf
(available soon)
Sonification Examples
Fisher Data set (two overlapping clusters): The sonification examples
are the parents of a series of optimization steps, starting with a
random sonification and optimizing towards an audible separation of
chlusters. SFk is the parent of iteration k.
- SF1
(mp3, 28k)
- SF3
(mp3, 28k)
- SF5
(mp3, 28k)
- SF6
(mp3, 28k)
- SF7
(mp3, 28k)
- SF9
(mp3, 28k)
- SF10
(mp3, 28k) good audible clustering structure
- SF11
(mp3, 28k)
- SF12
(mp3, 28k)
- SF13
(mp3, 28k)
- SF14
(mp3, 28k)
- SF15
(mp3, 28k)
- SF17
(mp3, 28k)
- SF18
(mp3, 28k)
- SF19
(mp3, 28k)
- SF20
(mp3, 28k)
- SF21
(mp3, 28k)
- SF22
(mp3, 28k)
- SF23
(mp3, 28k)
- SF24
(mp3, 28k)
- SF25
(mp3, 28k)
- SF33
(mp3, 28k)
- SF34
(mp3, 28k)
- SF37
(mp3, 28k)
Iris data set (4d data with 3 clusters, 150 items): The sonification
examples are again the parents for the successive iterations during
evolutionary optimization SIk denotes (S)ound Example for (I)ris data
set iteration k.
- SI1
(mp3, 40k)
- SI2
(mp3, 40k)
- SI3
(mp3, 40k)
- SI4
(mp3, 40k)
- SI5
(mp3, 40k)
- SI6
(mp3, 40k)
- SI7
(mp3, 40k)
- SI8
(mp3, 40k)
- SI9
(mp3, 40k)
- SI10
(mp3, 40k)
The following examples are optimization results for increased attention
to amplitude and panning
modified 2007-02-09,
thermann(at)techfak.uni-bielefeld.de