View License

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video

Highlights from
Gaussian Surprise and Running Windowed Mean / Variance

Be the first to rate this file! 6 Downloads (last 30 days) File Size: 17.6 KB File ID: #33573 Version: 1.5
image thumbnail

Gaussian Surprise and Running Windowed Mean / Variance



01 Nov 2011 (Updated )

Compute the Gaussian/Gamma surprise/saliency of data as well as its windowed mean/variance

| Watch this File

File Information

This code calculates the (windowed!) running mean and variance as well as
the (windowed) Gaussian surprise for each newly added element. Furthermore,
it is possible to calculate the univariate Gamma surprise.

The code comes with two examples on acoustic saliency/surprise using the
(synthetic) chirp signal and a real-world, meeting room audio recording.

Please see [1] for details and an application of the Gaussian windowed
surprise. See [2] for details on the univariate Gamma model. Be so kind
to cite [1] and/or [2], if you use the provided code.

[1] B. Schauerte, B. Kuehn, K. Kroschel, R. Stiefelhagen, "Multimodal
    Saliency-based Attention for Object-based Scene Analysis," in Proc.
    Int. Conf. Intelligent Robots and Systems (IROS), 2011.

[2] B. Schauerte, R. Stiefelhagen, ""Wow!" Bayesian Surprise for Salient
    Acoustic Event Detection". In Proc. 38th Int. Conf. Acoustics,
    Speech, and Signal Processing (ICASSP), 2013.

MATLAB release MATLAB 7.12 (R2011a)
Tags for This File   Please login to tag files.
Please login to add a comment or rating.
Comments and Ratings (2)
20 Dec 2011 Boris Schauerte

Hi Adam, if you send me the data (you will find my e-mail address on my web page), I will take a closer look at the issue (I tested the code on data from audio, some image processing, ... - so my experience does not cover all kinds of data). However, some first ideas: you could/should try both estimation methods and also have a closer look at the min_variance_value. Bests, Boris

Comment only
20 Dec 2011 Adam

Adam (view profile)

Hi, I can get the example scripts to run fine, but when I apply this to a data set of mine, I get all Nan for the surprise variable, even though the windowed mean and variance some out ok. Any idea why this is?

Comment only
02 Nov 2011 1.1

- set the numerically more stable variance estimation as default
- minor interface adaptation of the C/C++ code

16 Nov 2011 1.2

- added a help
- minor C/C++ interface changes

05 Feb 2012 1.3

improved the documentation and added an example script

27 Nov 2012 1.4

- added two examples

07 Mar 2013 1.5

- added the univariate Gamma model

Contact us