changeset 10:53ace3ec800c

Merge branch 'develop’. Updated documentation.

Binary file MASSEF.png has changed

--- a/README.md	Thu Mar 02 15:46:20 2017 +0000
+++ b/README.md	Fri Mar 03 10:37:21 2017 +0000
@@ -4,7 +4,7 @@
 
 ![MASSEF](/MASSEF.png?raw=true "MASSEF")
 
-The multichannel audio source separation evaluation framework is designed to facilitate the development and evaluation of audio source separation algorithms. The framework generates the mixture(s), calculates the ideal binary and ratio masks, provides the mixture(s) to the separation algorithm(s), and evaluates the outputs of the separation algorithm(s). The framework can also evaluate the ideal masks for the purposes of comparison.
+The multichannel audio source separation evaluation framework is designed to facilitate the development and evaluation of audio source separation algorithms. The framework generates the mixture(s), provides the mixture(s) to the separation algorithm(s), and evaluates the outputs of the separation algorithm(s). The framework can also calculate and evaluate the ideal masks for the purposes of comparison.
 
 Sources may have any number of channels; the framework evaluates each channel. The use of [`iosr.bss.mixture`](https://github.com/IoSR-Surrey/MatlabToolbox) objects facilitate the evaluation of spatialised mixtures (e.g. binaural).
 
@@ -15,11 +15,14 @@
 1. by providing [`iosr.bss.mixture`](https://github.com/IoSR-Surrey/MatlabToolbox) objects and separation algorithms, or
 2. by providing estimate and true source wav files.
  
-If 1), the framework generates the mixture(s), calculates the ideal binary and ratio masks, provides the mixture(s) to the separation algorithm(s), and evaluates the outputs of the separation algorithm(s). The framework also evaluates: the ideal masks for the purposes of comparison, and any azimuth/elevation estimates returned by the algorithm. Use the `execute()` method to operate in this mode.
+If 1), the framework operates as described above. In addition, the framework can:
+ * evaluate localisation accuracy (if the algorithm performs localisation) of any azimuth/elevation estimates returned by the algorithm, and
+ * evaluate time-frequency mask accuracy (if the algorithm calculates one).
+Use the `MASSEF.execute()` method to operate in this mode.
 
-If 2), the framework evaluates only the supplied estimate(s) using signal-related metrics. Use the `evaluate()` method to operate in this mode.
+If 2), the framework evaluates only the supplied estimate(s) using signal-related metrics. Use the `MASSEF.evaluate()` method to operate in this mode.
 
-The framework performs evaluations using a range of metrics, including SNR, [BSSeval and PEASS](http://bass-db.gforge.inria.fr/peass/), and [STOI](http://amtoolbox.sourceforge.net/amt-0.9.8/doc/models/taal2011.php). If the algorithm is intended to perform localisation, then this can also be evaluated.
+The framework performs evaluations using a range of metrics, including SNR, [BSSeval and PEASS](http://bass-db.gforge.inria.fr/peass/), and [STOI](http://amtoolbox.sourceforge.net/amt-0.9.8/doc/models/taal2011.php).
 
 ## Requirements
 

--- a/help_html/source/help_Example.m	Thu Mar 02 15:46:20 2017 +0000
+++ b/help_html/source/help_Example.m	Fri Mar 03 10:37:21 2017 +0000
@@ -1,11 +1,11 @@
 %% Example
 % 
-%% First Steps 
+%% First steps 
 
 MASSEF.install; % you only need to do this once!
 MASSEF.start; % start MASSEF
 
-%% Make Mixtures
+%% Make mixtures
 % Specify the source files:
 
 target_fns = {'s1.wav','s2.wav'}; % target filenames
@@ -54,7 +54,7 @@
     )...
 );
 
-%% Instantiate the Separation Algorithm
+%% Instantiate the separation algorithm
 
 p = messl_massef(fs);
 

--- a/help_html/source/help_Index.m	Thu Mar 02 15:46:20 2017 +0000
+++ b/help_html/source/help_Index.m	Fri Mar 03 10:37:21 2017 +0000
@@ -2,13 +2,14 @@
 % 
 %% Overview
 % 
+% <<../MASSEF.png>>
+% 
 % The multichannel audio source separation evaluation framework is designed
-% to faciliate the development and evaluation of audio source separation
-% algorithms. The framework generates the mixture(s), calculates the ideal
-% binary and ratio masks, provides the mixture(s) to the separation
-% algorithm(s), and evaluates the outputs of the separation algorithm(s).
-% The framework also evaluates the ideal masks for the purposes of
-% comparison.
+% to facilitate the development and evaluation of audio source separation
+% algorithms. The framework generates the mixture(s), provides the
+% mixture(s) to the separation algorithm(s), and evaluates the outputs of
+% the separation algorithm(s). The framework can also calculate and
+% evaluate the ideal masks for the purposes of comparison.
 % 
 % Sources may have any number of channels; the framework evaluates each
 % channel. The use of iosr.bss.mixture objects facilitate the evaluation of
@@ -31,9 +32,9 @@
 % 
 % Before using the framework, you need to download and install its
 % dependencies. This can be done automatically using the
-% <help_MASSEF_install.html MASSEF.install> method. Before each session,
+% <help_MASSEF_install.html MASSEF.install()> method. Before each session,
 % MASSEF needs to be started using the <help_MASSEF_start.html
-% MASSEF.start> method.
+% MASSEF.start()> method.
 % 
 %% Usage 
 % 
@@ -42,17 +43,20 @@
 % # by providing |iosr.bss.mixture| objects and separation algorithms, or
 % # by providing estimate and true source wav files.
 %   
-% If 1), the framework generates the mixture(s), calculates the ideal
-% binary and ratio masks, provides the mixture(s) to the separation
-% algorithm(s), and evaluates the outputs of the separation algorithm(s).
-% The framework also evaluates: the ideal masks for the purposes of
-% comparison, and any azimuth/elevation estimates returned by the
-% algorithm. Use the <help_MASSEF_execute.html execute> method to operate
-% in this mode.
+% If 1), the framework operates as described above. In addition, the
+% framework can:
+% 
+% * evaluate localisation accuracy (if the algorithm performs localisation)
+% of any azimuth/elevation estimates returned by the algorithm, and
+% * evaluate time-frequency mask accuracy (if the algorithm calculates
+% one).
+% 
+% Use the <help_MASSEF_execute.html MASSEF.execute()> method to operate in
+% this mode.
 % 
 % If 2), the framework evaluates only the supplied estimate(s) using
-% signal-related metrics. Use the <help_MASSEF_evaluate.html evaluate>
-% method to operate in this mode.
+% signal-related metrics. Use the <help_MASSEF_evaluate.html
+% MASSEF.evaluate()> method to operate in this mode.
 % 
 % <html>
 % <hr>