import code sent by Gerard Roma
| author |
Dan Stowell <dan.stowell@elec.qmul.ac.uk> |
| date |
Fri, 01 Nov 2013 08:48:19 +0000 |
| parents |
|
| children |
def2b3fa1450 |
| rev |
line source |
|
dan@0
|
1 The files in this folder represent our submission for the Scene Classificatoin task of the IEEE D-CASE AASP Challenge (http://c4dm.eecs.qmul.ac.uk/sceneseventschallenge/)
|
|
dan@0
|
2
|
|
dan@0
|
3 The code has been tested mainly on Matlab2012 on OSX
|
|
dan@0
|
4 Required libraries: rastamat and libsvm
|
|
dan@0
|
5
|
|
dan@0
|
6 The implemented approach is described in:
|
|
dan@0
|
7 G. Roma, W. Nogueira, P.Herrera, _Recurrence Quantification Analysis Features for Environmental Sound Recognition_. Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. New Paltz, USA 2013.
|
|
dan@0
|
8
|
|
dan@0
|
9 The main files are:
|
|
dan@0
|
10
|
|
dan@0
|
11 * classify_scenes.m
|
|
dan@0
|
12 * analyze_files.m
|
|
dan@0
|
13 * RQA.m
|
|
dan@0
|
14
|
|
dan@0
|
15 The rest of matlab files can be used to test the code. Some of the files are taken from: https://soundsoftware.ac.uk/projects/aasp-d-case-metrics
|
|
dan@0
|
16
|
|
dan@0
|
17 Two submissions were sent to the challenge, one uses hardcoded SVM parameters, the other does grid search:
|
|
dan@0
|
18
|
|
dan@0
|
19 classify_scenes(tmp_path, train_file,test_file, output_file, 0) % use hardcoded parameters for SVM
|
|
dan@0
|
20 classify_scenes(tmp_path, train_file,test_file, output_file, 1) % use grid search
|
|
dan@0
|
21
|
|
dan@0
|
22 The temp_path is used to store features.
|
|
dan@0
|
23
|
