Changeset 2606 for Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook.pm

Timestamp:

06/09/08 17:06:50 (6 months ago)

Author:

kmaclean

Message:

refacture to create Chapter, Segments & MissingWords? classes - snapshop

Files:

• Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook.pm (modified) (13 diffs)

Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook.pm

@@ -1 +1 @@
-#! /usr/bin/perl
-
+.1
-
-=head1 NAME
-
-15 word audio segments (approximately) 
+audio segments
-
-=cut 
-
-
+ 
-use strict;
-use diagnostics;
@@ -15 +15 @@
-use File::Basename;
-use File::Copy;
-
+
-use AudioBook::Audio;
-use AudioBook::Text;
-use AudioBook::Dictionary;
-
+use AudioBook::Segments; 
+use AudioBook::MissingWords;
+use AudioBook::Chapter;
+
+
+
-=head1 SYNOPSIS
-
-       
+
- $./AudioBook -a speechfile.wav -t text.txt             minimal run configuration
-
@@ -52 +58 @@
-                 * required for script to run
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-=head3 Text Does not Match Audio
-
-
-
+
+
+
+
+
-
-If there are a large divergence in the text from the speech audio, then you will have to manually listen to the speech audio to determine 
-where the biggest transcription errors lie, and then modify the original text file to match the speech audio file.  
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-The verify switch performs a forced alignment on the individual segments generated from the first pass forced alignment.  Low scores 
-(i.e. the lowest average log likelihood per frame score) indicate that the transcription text might not match the corresponding audio 
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-The pronunciations generated by the Sequitor G2P scripts need to be manually reviewed before any new pronunciations are added to the
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-=head1 ALGORITHM
+
+=head2 Audio Segmentation
-
-This program tries to segments the speech audio file into 15 word sentences.  However, if the pause following the 15th word relative to the current 
@@ -103 +171 @@
-The default pause duration is 2000000 in units of 100ns.  This can be changed (using the "-p" switch") if the speech audio file does segment well 
-enough with this default.
+
+=head2 Generating Out-of-Vocabulary Word Pronunciations
+
+The script gets Sequitor to generate the 20 likeliest pronunciations for each OOV, and then add it to the dict file.  It then performs
+another forced aligment on the audio segment containing the Out-of-Vocabulary word.  Hvite will take the sequence of phoneme sounds that it 
+recognizes and try to match it to one of the possible pronunciations in the dictionary.  We are therefore using the audio to automatically 
+help generate the correct pronunciation.  Because the VoxForge Aoustic models are not that accurate, these suggestions need to be validated 
+and compared with the pronunications generated by Sequitor, and a judgment call needs to be made to select the correct pronunciations.
+
+=head1 REQUIREMENTS
+
+=item 1 - Sequitor G2P trainable Grapheme-to-Phoneme converter (GPL v2; requires Python to be installed)
+
+        http://www-i6.informatik.rwth-aachen.de/web/Software/g2p.html
+
+=item 2 - HTK Hidden Markov Model Toolkit (note: the source is "open" - i.e. you can read the code, but there are distribution restrictions)
+
+        http://htk.eng.cam.ac.uk/
+        
+        The HTK toolkit needs to be in your path 
+        (see http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/download)
-
-=cut 
@@ -139 +228 @@
-=head2 process
-
-ement the user designated speech audio file (-a) 
+ment the user designated speech audio file (-a) u
-
-=cut
@@ -145 +234 @@
-sub process {
-        my ($self)= @_;
-        my $debug = $self->{'debug'};
-        my $audiofile = $self->{"audiofile"};
-        my $textfile = $self->{"textfile"};
-        my $username = $self->{"username"};
-        my $tarSuffix = $self->{"tarSuffix"};
-        my $pronDict = $self->{"pronDict"};
-        my $htk_files = $self->{'htk_files'};
-        my $log = $self{'log'};
-        my $dict = "AudioBook/interim_files/dict";
-        my $originalDict = "AudioBook/interim_files/originalDict";
-        my $altDict = "AudioBook/interim_files/altDict";        
-        my $prompts = "AudioBook/interim_files/prompts";        
-        
-
-
-
-
-
+
+
+
+
+
+
+
-        
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
-        
-        if (defined($tarSuffix)){
-                _createTarFile($self);
-
+      
-}
-
@@ -295 +343 @@
-        my $debug = $self->{'debug'};   
-        getopts('a:b:d:hl:m:p:r:s:t:u:x:q:vwST');    #  sets $opt_* as a side effect.
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                $self->{"audiofile"}="AudioBook/test/audio.wav";
-f
-f
+F
+F
-                $command = ("cp AudioBook/input_files/VoxForgeDict AudioBook/interim_files/VoxForgeDict"); print "cmd:$command\n"; system($command);
-                $self->{"pronDict"}="AudioBook/interim_files/VoxForgeDict";
@@ -319 +397 @@
-                }
-                if (-r $opt_t) {
-f
-
-f
+F
+
+F
-                }
-                if (defined($opt_d)) {
@@ -403 +481 @@
-                        }
-                }
-        } elsif ($opt_h) {
-                print "\nVoxForge Audio Segmentation Script Parameters\n";      
-                print   "=============================================\n";      
-                print "-a\t* audio file name (WAV format only)\n";
-                print "-b\tnotify if beam width for Forced Alignment exceeds a certain level (default = 250)\n";
-                print "\t(does not set HVite's beam width parameter)\n";
-                print "-d\tpronunciation dictionary  (default = AudioBook/input_files/VoxforgeDict)\n";
-                print "-h\tshow help\n";        
-                print "-l\tLICENSE file (default = AudioBook/input_files/LICENCE)\n";
-                print "-m\tTarget maximum sentence length (default = $default_max_sentence_length words)\n";
-                print "-p\tMinimum pause for sentence break (default = $default_min_pause_for_sentence_break in units of 100ns)\n";             
-                print "-q\tlog words with single quotes (default = yes)\n";             
-                print "-r\tREADME file (default = AudioBook/input_files/README)\n";                             
-                print "-s\tAverage sentence length (default = $default_average_sentence_length words)\n";                               
-                print "-t\t* text file name (containing transcriptions of speech in audio file)\n";
-                
-                print "-u\tusername or name you want file stats collected by on VoxForge Metrics \n";
-                print "\tpage:\t(http://www.voxforge.org/home/downloads/metrics)\n";    
-                
-                print "-v\tvalidate segment audio files to prompt text using forced Aligment\n";
-                print "-w\tvalidate missing word pronunciations to audio recordings\n";         
-                print "-x\tunique tar file suffix (max 3 characters - remainder is truncated)\n";
-                print "-S\trun sanity test\n";          
-                print "-T\tcreate gzipped/tar file\n";
-                print "\n\t* required for script to run\n";     
-                print "\n";     
-                print "--\n";                   
-                print "Free Speech... Recognition\n";
-                print "http://www.voxforge.org\n\n";
-                exit;
-        } else {
-                print "\nVoxForge Audio Segmentation Script\n"; 
@@ -443 +491 @@
-        }
-        print "audiofile:" . $self->{"audiofile"}. "\n";
-file:" . $self->{"textf
+File:" . $self->{"textF
-        print "pronDict:" . $self->{"pronDict"} . "\n\n";       
-}
-
-- Public (used by methods in other sub-classes)
+
-
-=item * getAverage_sentence_length()
@@ -458 +506 @@
-}
-
+=item * getBeam_width()
+
+=cut
+
+sub getBeam_width {
+        my $self = shift;
+        return $self->{"beam_width"};
+}
+
-=item * getMax_sentence_length()
-
@@ -473 +530 @@
-sub getMin_pause_for_sentence_break {
-        my $self = shift;
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-=head1 Change Log    
-
-
-
+
+
+
-        
-=cut
@@ -501 +653 @@
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
+
+=cut
+
+1;