Mercurial > hg > massef

comparison help_html/source/help_Index.m @ 0:e34a535b9af0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Initial beta release.
author Christopher Hummersone <c.hummersone@surrey.ac.uk>
date Thu, 02 Mar 2017 09:44:08 +0000
parents
children 3c754d051479
comparison
equal deleted inserted replaced
-1:000000000000 0:e34a535b9af0
1 %% Multichannel audio source separation evaluation framework (MASSEF)
2 %
3 %% Overview
4 %
5 % The multichannel audio source separation evaluation framework is designed
6 % to faciliate the development and evaluation of audio source separation
7 % algorithms. The framework generates the mixture(s), calculates the ideal
8 % binary and ratio masks, provides the mixture(s) to the separation
9 % algorithm(s), and evaluates the outputs of the separation algorithm(s).
10 % The framework also evaluates the ideal masks for the purposes of
11 % comparison.
12 %
13 % Sources may have any number of channels; the framework evaluates each
14 % channel. The use of iosr.bss.mixture objects facilitate the evaluation of
15 % spatialised mixtures (e.g. binaural).
16 %
17 % The framework comprises two main classes:
18 %
19 % * <help_MASSEF.html MASSEF>&mdash;multichannel audio source separation
20 % evaluation framework class.
21 % * <help_MASSEFresults.html MASSEFresults>&mdash;the results class used by
22 % MASSEF.
23 %
24 % <help_Example.html View an example of the use of these classes.>
25 %
26 % MASSEF can be used to evaluate and compare binaural separation algorithms,
27 % provided that the algorithms conform to the <help_Separators.html
28 % required format>.
29 %
30 %% Installation
31 %
32 % Before using the framework, you need to download and install its
33 % dependencies. This can be done automatically using the
34 % <help_MASSEF_install.html MASSEF.install> method. Before each session,
35 % MASSEF needs to be started using the <help_MASSEF_start.html
36 % MASSEF.start> method.
37 %
38 %% Usage
39 %
40 % The framework can be run in two ways:
41 %
42 % # by providing |iosr.bss.mixture| objects and separation algorithms, or
43 % # by providing estimate and true source wav files.
44 %
45 % If 1), the framework generates the mixture(s), calculates the ideal
46 % binary and ratio masks, provides the mixture(s) to the separation
47 % algorithm(s), and evaluates the outputs of the separation algorithm(s).
48 % The framework also evaluates: the ideal masks for the purposes of
49 % comparison, and any azimuth/elevation estimates returned by the
50 % algorithm. Use the <help_MASSEF_execute.html execute> method to operate
51 % in this mode.
52 %
53 % If 2), the framework evaluates only the supplied estimate(s) using
54 % signal-related metrics. Use the <help_MASSEF_evaluate.html evaluate>
55 % method to operate in this mode.
56 %
57 % <html>
58 % <hr>
59 % <p>Copyright &copy; 2016 <a href="http://www.surrey.ac.uk">University of Surrey</a><br>
60 % <a href="http://iosr.uk">Institute of Sound Recording, University of Surrey, UK</a></p>
61 % </html>