voxforge.org
VoxForge Dev
Home · Read · Listen · AudioBooks · Forums · Dev · Downloads · About

Changeset 2585

Show
Ignore:
Timestamp:
05/14/08 22:06:47 (5 months ago)
Author:
kmaclean
Message:

AudioSegmentation script - snapshot

Files:

Legend:

Unmodified
Added
Removed
Modified
Copied
Moved

  • Trunk/Scripts/Audio_scripts/AudioSegmentation

    • Property svn:ignore changed from

      hoe.wav
      hoe-16-original.wav
      hoe-original.wav
       to
      hoe.wav
      hoe-16-original.wav
      hoe-original.wav
      bluefox83-20080413-bwq.tgz
      bluefox83-20080512

  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook.pm

    r2578 r2585  
    3636### Class Variables 
    3737#################################################################### 
    38 our($opt_a,$opt_d,$opt_h,$opt_l,$opt_r,$opt_t,$opt_x,$opt_K,$opt_T,); # need to define these because using strict. 
     38our($opt_a,$opt_d,$opt_h,$opt_l,$opt_r,$opt_t,$opt_x,$opt_K,$opt_T,$opt_u); # need to define these because using strict. 
    3939my %self; 
    4040$self{'debug'} = 0; 
    …… 
    7272                $dictionary->updatePronDict(); 
    7373                # need to update dict with missing words 
    74          
     74                # can't seem to change default HDMan log file with "-l" parameter 
     75                $command = ("cp AudioBook/interim_files/dlog AudioBook/interim_files/dlog1"); print "cmd:$command\n" if $debug; system($command); 
    7576                $command = ("HDMan -A -D -T 1 -g $htk_files/global.ded -m -w AudioBook/interim_files/wlist -i -l AudioBook/interim_files/dlog AudioBook/interim_files/dict $voxforgeDict"); system($command) == 0 or confess "fullrun $command failed: $?"; 
     77                $command = ("mv AudioBook/interim_files/dlog AudioBook/interim_files/dlog2"); print "cmd:$command\n" if $debug; system($command); 
    7678                $command = ("cp AudioBook/interim_files/MissingWords_out AudioBook/output_files/MissingWords"); print "cmd:$command\n" if $debug; system($command); 
    7779        } else { 
    …… 
    121123        my ($self)= @_; 
    122124        getopts('a:d:hl:r:t:u:x:KT');    #  sets $opt_* as a side effect. 
    123         if ($opt_a and $opt_t and $opt_d) {    
     125        if ($opt_a and $opt_t) {       
    124126                if (-r $opt_a) { 
    125127                        $self->{"audiofile"}=$opt_a; 
    …… 
    132134                        die "can't open -t" . $self->{"textfile"} . "\n";                
    133135                } 
    134                 if (-r $opt_d) { 
    135                         $self->{"voxforgeDict"}=$opt_d; 
     136                if (defined($opt_d)) { 
     137                        if (-r $opt_d) { 
     138                                $self->{"voxforgeDict"}=$opt_d; 
     139                        } else { 
     140                                die "can't open -d" . $self->{"voxforgeDict"} . "\n";    
     141                        } 
    136142                } else { 
    137                         die "can't open -d" . $self->{"voxforgeDict"} . "\n";          
     143                        $self->{"voxforgeDict"}="AudioBook/input_files/VoxForgeDict";  
    138144                } 
    139145                ### 
    …… 
    142148                                $self->{"tarSuffix"}=substr($opt_x,3); # only use 1st 3 characters.                      
    143149                        }else { 
    144                                 $self->{"tarSuffix"}=random_characters(3); 
     150                                $self->{"tarSuffix"}=_random_characters(3); 
    145151                        } 
    146          
     152                        if ($opt_u) { 
     153                                $self->{"username"}=$opt_u;      
     154                        }else { 
     155                                $self->{"username"}="anonymous"; 
     156                        }        
    147157                        if ($opt_r) { 
    148158                                if (-r $opt_r) { 
    …… 
    168178                #$self->{"textfile"}="AudioBook/test/text-simple.txt"; 
    169179                $self->{"textfile"}="AudioBook/test/text-original.txt"; 
    170                 $self->{"voxforgeDict"}="AudioBook/test/VoxForgeDict"; 
     180                $command = ("cp AudioBook/input_files/VoxForgeDict AudioBook/interim_files/VoxForgeDict"); system($command); 
     181                $self->{"voxforgeDict"}="AudioBook/interim_files/VoxForgeDict"; 
    171182                $self->{"tarSuffix"}=_random_characters(3); 
    172183                $self->{"username"}="test"; 
    …… 
    175186                print   "=============================================\n";       
    176187                print "-a\t* audio file name\n"; 
    177                 print "-d\t* pronunication dictionary\n"; 
     188                print "-d\t pronunciation dictionary  (default = AudioBook/input_files/VoxforgeDict)\n"; 
    178189                print "-h\tshow help\n";         
    179190                print "-l\tLICENSE file (default = AudioBook/input_files/LICENCE)\n";    
    …… 
    182193                print "-u\tusername or name you want file stats collected by on VoxForge Metrics \n"; 
    183194                print "\tpage:\t(http://www.voxforge.org/home/downloads/metrics)\n";     
     195                print "-x\tunique tar file suffix (max 3 characters - remainder is truncated)\n"; 
    184196                print "-K\trun test\n";          
    185                 print "-T\tunique tar file suffix - also acts a switch to create gzipped/tar file\n"; 
    186                 print "\t(max 3 characters - remainder is truncated)\n";                 
    187                 print "\n\t* required for scripts to run\n";     
     197                print "-T\tcreate gzipped/tar file\n"; 
     198                print "\n\t* required for script to run\n";      
    188199                print "\n";      
    189200                exit; 

  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook/Audio.pm

    r2576 r2585  
    3838### Class Variables 
    3939#################################################################### 
    40 my $average_sentence_length = 8; 
    41 my $max_sentence_length = 12; 
     40my $average_sentence_length = 13; 
     41my $max_sentence_length = 18; 
    4242#my $min_pause_for_sentence_break = 200000; # HTK time format - 100 millisecond increments 
    43 my $min_pause_for_sentence_break = 1500000; 
     43my $min_pause_for_sentence_break = 5000000; 
    4444my (@max_sentences, $max_sentence_length_found, $max_sentence_length_linenumber, $min_sentence_length_linenumber); 
    4545my $min_sentence_length_found = $max_sentence_length; 
    …… 
    140140        $filename_nosuffix  =~ s/\.//;   
    141141        $self->{"filename"} = $filename;         
     142        $self->{"filename_nosuffix"} = $filename_nosuffix; 
    142143        $self->{"filename_nopath"} = $filename_nopath; 
    143         $self->{"filename_nosuffix"} = $filename_nosuffix; 
     144        $self->{"filename_prefix"} = lc(substr($filename_nopath,0,3)); 
    144145        $self->{"textContents"} = $textContents; 
    145146 
    …… 
    200201        $command = ("rm AudioBook/interim_files/temp.wav"); print "cmd:$command\n" if $debug; system($command); 
    201202         
    202         print "### segment summary: ################################################################\n";          
     203        print "### segment summary: #######################################################\n"; 
     204        print "\nSettings:average_sentence_length->$average_sentence_length;max_sentence_length->$max_sentence_length\n"; 
     205        print   "         pause length:$min_pause_for_sentence_break (" . $min_pause_for_sentence_break/10000000 . " seconds)\n";         
    203206        print "\nSentence Length: min:$min_sentence_length_linenumber->$min_sentence_length_found; max:$max_sentence_length_linenumber->$max_sentence_length_found\n"; 
    204207        print "\nSentences over max_sentence_length of $max_sentence_length words:\n"; 
    …… 
    206209                print "\t$line\n"; 
    207210        }        
    208         print "\n#####################################################################################\n"; 
     211        print "\n###########################################################################\n"; 
    209212} 
    210213 
    …… 
    212215        my ($self, $where, $increment,$aligned_words, $fileid, $sentence_start, $sentence_end) = @_; 
    213216        my $debug = $self->{"debug"};    
    214         my $filename_nosuffix = $self->{"filename_nosuffix"}; 
     217        my $filename_prefix = $self->{"filename_prefix"}; 
    215218         
    216219        my @aligned_line = split(/\s/,$$aligned_words[$$sentence_end + $increment]); 
    …… 
    220223                my $count; 
    221224                my $padded_fileid = sprintf("%04d",$$fileid); 
    222                 print PROMPTS "$filename_nosuffix$padded_fileid ";     
     225                print PROMPTS "$filename_prefix$padded_fileid ";       
    223226                for ($count = $$sentence_start; $count <= $$sentence_end + $increment; $count++) { 
    224227                                my @aligned_line = split(/ /,$$aligned_words[$count]); 
    …… 
    259262                _processAudio ($self,$startTime,$endTime,$padded_fileid) ; 
    260263                # !!!!!! 
    261                 _calculateStats($self,$sentence_start,$sentence_end,\$increment,$filename_nosuffix,$padded_fileid); 
     264                _calculateStats($self,$sentence_start,$sentence_end,\$increment,$filename_prefix,$padded_fileid); 
    262265                # !!!!!! 
    263                 #print "$filename_nosuffix$padded_fileid:$wordcount\n"; # !!!!!! 
     266                #print "$filename_prefix$padded_fileid:$wordcount\n"; # !!!!!! 
    264267            # Reset everthing to start looking for next set words delimited by a pause           
    265268                $$sentence_start = ($$sentence_end + $increment) + 1; 
    …… 
    272275 
    273276sub _calculateStats { # Calculate min and max sentence 
    274         my ($self,$sentence_start,$sentence_end,$increment,$filename_nosuffix,$padded_fileid ) = @_; 
     277        my ($self,$sentence_start,$sentence_end,$increment,$filename_prefix,$padded_fileid ) = @_; 
    275278        my $debug = $self->{"debug"};    
    276279         
    …… 
    286289         
    287290        if ($sentence_length>$max_sentence_length) { 
    288                 push (@max_sentences,"$filename_nosuffix$padded_fileid:" . $sentence_length+1); 
    289         } elsif ($sentence_length<$min_sentence_length_found) { 
     291                push (@max_sentences,"$filename_prefix$padded_fileid:" . ($sentence_length+1)); 
     292        }  
     293        if ($sentence_length<$min_sentence_length_found) { 
    290294        $min_sentence_length_found = $sentence_length+1;  
    291                 $min_sentence_length_linenumber = "$filename_nosuffix$padded_fileid"; 
     295                $min_sentence_length_linenumber = "$filename_prefix$padded_fileid"; 
    292296        } elsif ($sentence_length>$max_sentence_length_found) { 
    293297        $max_sentence_length_found = $sentence_length+1; 
    294         $max_sentence_length_linenumber = "$filename_nosuffix$padded_fileid"; 
     298        $max_sentence_length_linenumber = "$filename_prefix$padded_fileid"; 
    295299        } 
    296300} 
    …… 
    299303        my ($self, $aligned_words, $fileid, $sentence_start, $sentence_end) = @_; 
    300304        my $debug = $self->{"debug"};    
    301         my $filename_nosuffix = $self->{"filename_nosuffix"}; 
     305        my $filename_prefix = $self->{"filename_prefix"}; 
    302306        my ($count, $startTime); 
    303307         
    304308        #print "!!!!!!_last_sentence\n"; 
    305309        my $padded_fileid = sprintf("%04d",$$fileid); 
    306         print PROMPTS "$filename_nosuffix$padded_fileid ";                             
     310        print PROMPTS "$filename_prefix$padded_fileid ";                               
    307311        for ($count = $$sentence_start; $count <= $#$aligned_words; $count++) { 
    308312                my @aligned_line = split(/ /,$$aligned_words[$count]); 
    309313                my ($word,$startTime,$endTime,$pause) = @aligned_line ; 
    310                 #print $filename_nosuffix . $#$aligned_words . "last aligned_line:@aligned_line:end\n";  # !!!!!! 
     314                #print $filename_prefix . $#$aligned_words . "last aligned_line:@aligned_line:end\n";  # !!!!!! 
    311315        print PROMPTS ("$word "); 
    312316        } 
    …… 
    334338        my $process_audio = $self->{"process_audio"}; 
    335339        my $samplerate = $self->{"samplerate"}; 
    336         my $filename_nosuffix = $self->{"filename_nosuffix"}; 
     340        my $filename_prefix = $self->{"filename_prefix"}; 
    337341        my $filename_nopath = $self->{"filename_nopath"}; 
    338342        my $htk_files = $self->{'htk_files'}; 
    …… 
    346350                $command = ("HCopy -C $htk_files/copy_config  -s $startTime -e $endTime AudioBook/interim_files/$filename_nopath AudioBook/interim_files/temp.wav"); print "cmd:$command\n" if $debug; system($command);  
    347351                # sox command to create a proper wav file with a RIFF header;  
    348                 $command = ("sox  -t .raw -r $samplerate -sw AudioBook/interim_files/temp.wav AudioBook/output_files/wav/$filename_nosuffix$padded_fileid.wav"); print "cmd:$command\n" if $debug; system($command);   
    349                 print "AudioBook/output_files/wav/$filename_nosuffix$padded_fileid.wav\n" if not $debug; 
     352                $command = ("sox  -t .raw -r $samplerate -sw AudioBook/interim_files/temp.wav AudioBook/output_files/wav/$filename_prefix$padded_fileid.wav"); print "cmd:$command\n" if $debug; system($command);     
     353                print "AudioBook/output_files/wav/$filename_prefix$padded_fileid.wav\n" if not $debug; 
    350354        } else { 
    351                 print "AudioBook/output_files/wav/$filename_nosuffix$padded_fileid.wav\t$startTime:$endTime:\n" if $debug; 
     355                print "AudioBook/output_files/wav/$filename_prefix$padded_fileid.wav\t$startTime:$endTime:\n" if $debug; 
    352356        } 
    353357} 
    …… 
    365369} 
    366370 
    367 sub getFilename__nosuffix { 
     371sub filename_prefix { 
    368372        my $self = shift; 
    369         return $self->{"filename_nosuffix"} ; 
     373        return $self->{"filename_prefix"} ; 
    370374} 
    3713751; 

  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook/Dictionary.pm

    r2578 r2585  
    116116        open(DICTIONARY,">>$voxforgeDict") or confess ("cannot open $voxforgeDict file"); 
    117117        open(MISSINGWORDSOUT,"<$missing_words_out") or confess ("cannot open $missing_words_out file"); 
    118         print "adding the following words to VoxForge Pronunicaiton Dictionary\n"; 
     118        print "adding the following words to VoxForge Pronunciation Dictionary\n"; 
    119119        while (my $line = <MISSINGWORDSOUT>) { 
    120120                next if ($line =~ /^(\s)*$/);  # skip blank lines 

  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook/Text.pm

    r2578 r2585  
    2727use diagnostics; 
    2828use Carp; 
     29 
     30use Lingua::EN::Numbers qw(num2en num2en_ordinal); 
     31use Lingua::EN::Numbers::Years; 
    2932#################################################################### 
    3033### Constructor 
    …… 
    5558                $line =~ tr/a-z/A-Z/; # change to uppercase 
    5659                $line =~ s/,//g; # remove commas  
    57                 $line =~ s/\.\"/ /g;  
    58                 $line =~ s/\.\'/ /g;  
    59                 # !!!!!!  
     60                $line =~ s/\.\"/ /g; # period followed by double quote 
     61                $line =~ s/\.\'/ /g; # period followed by single quote 
     62                # !!!!!! see below for processing of periods  
    6063                #line =~ s/\./ /g; # remove periods # too broad - periods in emails or URLs are pronounced, but need to avoid acronyms. 
    61                 $line =~ s/\./ /g; # remove periods 
    6264                # !!!!!! 
    6365                #  $line =~ s/\'//g; # remove single quotes; but need words like "don't" - need to research this more ... 
    …… 
    8688                                $word =~ s/^\'+//; # remove single quote(s) from beginning of word 
    8789                                $word =~ s/\'+$//; # remove single quote(s) from end of word 
    88                                 # !!!!!! 
    89                                 #push (@words, $word); 
    90                                 if ($word =~ /\d/) { # word contains numbers 
    91                                         processNumbers ($self, \@words, $word); 
     90                                if ($word =~ /[\w\-.]+@[\w\-.]+\.[A-Za-z]{2,4}/) { #email address 
     91                                        _processEmails($self, \@words, $word); 
     92                                #} elsif ($word =~ /(http|https|ftp):\/\/[\w\-.]+(:\d+)?\/[\w.\-~\/%]+/) { # url 
     93                                } elsif ($word =~ /(www\.)?(\w+)\.([A-Za-z]{2,4})/)  { # url                     
     94                                        _processUrls($self, \@words, $word); 
     95                                } elsif ($word =~ /\d/) { # word contains numbers 
     96                                        _processNumbers ($self, \@words, $word); 
     97                                } elsif ($word =~ /\./) {# $word contains a period  
     98                                        $word =~ s/\.//g; 
     99                                        push (@words, $word);                                    
    92100                                } else { 
    93101                                        push (@words, $word); 
    94102                                } 
    95                                 # !!!!!! 
    96103                        } 
    97104                } 
    …… 
    101108}  
    102109 
    103 sub processNumbers { 
     110sub _processEmails { #private 
     111        my ($self,$wordarray, $word)= @_; 
     112        my $debug = $self->{"debug"}; 
     113        if ($word =~ /\d/) { 
     114                confess "error - fix: $word contains numbers\n" 
     115        } elsif ($word =~ /(\w+)\@(\w+)\.(\w+)/)  { # only catches basic email address 
     116                push (@$wordarray, $1); 
     117                push (@$wordarray, "at"); 
     118                push (@$wordarray, $2); 
     119                push (@$wordarray, "dot"); 
     120                push (@$wordarray, $3); 
     121        } else { 
     122                confess "error - fix: $word\n" 
     123        } 
     124                 
     125} 
     126 
     127#while ($word =~ s/(\w+)\.(\w+)/g) { # how to loop regex results 
     128#       push (@words, $1); 
     129#       push (@words, "dot"); 
     130#       push (@words, $2);                       
     131#} 
     132sub _processUrls { #private 
     133        my ($self,$wordarray, $word)= @_; 
     134        my $debug = $self->{"debug"}; 
     135        print "processingUrls: $word\n";         
     136        if ($word =~ /(www)?\.(\w+)\.([A-Za-z]{2,4})/)  { # URL: www.abc.com 
     137                print "processingUrls: splitword:$1;DOT;$2;DOT;$3;\n";           
     138                push (@$wordarray, $1); 
     139                push (@$wordarray, "DOT");                               
     140                if ($2 =~ /\d+/) { 
     141                        _processWordsContainingNumbers ($self, $wordarray, $2); 
     142                } else { 
     143                        push (@$wordarray, $2); 
     144                } 
     145                push (@$wordarray, "DOT");       
     146                push (@$wordarray, $3); # can only be a top level domain name 
     147        } elsif ($word =~ /(\w+)\.([A-Za-z]{2,4})/)  { # URL: abc.com 
     148                my $word1 = $1; 
     149                my $word2 = $2; 
     150                print "processingUrls: splitword:$word1;DOT;$word2;\n";          
     151                if ($word1 =~ /\d+/) { 
     152                        print "processingUrls: splitword2:$word1;DOT;$word2;\n";  
     153                        _processWordsContainingNumbers ($self, $wordarray,$word1); 
     154                } else { 
     155                        push (@$wordarray, $word1); 
     156                } 
     157                push (@$wordarray, "DOT");                               
     158                push (@$wordarray, $word2); # can only be a top level domain name 
     159        } else { 
     160                confess "error - fix: $word\n" 
     161        } 
     162} 
     163 
     164sub _processWordsContainingNumbers { #private 
     165        my ($self,$wordarray, $subword)= @_; 
     166        my $debug = $self->{"debug"}; 
     167        # separates numbers contained in a word, and converts ordinal poriton of a words into its own word. 
     168        if ($subword =~ /\d+\D+/) {  # assume single, consecutive set of numbers (i.e no split numbers in word) 
     169                my $number = $subword; 
     170                print "processWordsContainingNumbers:subword:$subword;\n"; 
     171                $number =~ s/\D//g; # removes non-digit characters 
     172                print "processWordsContainingNumbers:number:$number\n"; 
     173                my @number = split(//, $number); 
     174                foreach my $digit (@number) { 
     175                        processNumbers ($self, $wordarray, $digit); # will push the resulting ordinal converted to a word onto the array 
     176                }                
     177                my $word = $subword; 
     178                $word =~ s/\d//g; # removes digits 
     179                if (defined($word) and ($word ne "")) { 
     180                        push (@$wordarray, $word); 
     181                }        
     182        } elsif ($subword =~ /\D+\d+/) { # assume single, consecutive set of numbers (i.e no split numbers in word) 
     183                my $word = $subword; 
     184                $word =~ s/\d//g; # removes digits 
     185                if (defined($word) and ($word ne "")) { 
     186                        push (@$wordarray, $word); 
     187                }        
     188                my $number = $subword; 
     189                print "processWordsContainingNumbers:subword:$subword;\n"; 
     190                $number =~ s/\D//g; # removes non-digit characters 
     191                print "processWordsContainingNumbers:number:$number\n"; 
     192                my @number = split(//, $number); 
     193                foreach my $digit (@number) { 
     194                        _processNumbers ($self, $wordarray, $digit); # will push the resulting ordinal converted to a word onto the array 
     195                }                        
     196                 
     197        }        
     198} 
     199         
     200sub _processNumbers { #private 
    104201        my ($self,$words, $number)= @_; 
    105202        my $debug = $self->{"debug"};    
    106203 
    107         if ($number =~ /^\d+,\d+/) { # comma separated number 
     204        if ($number =~ /^\d+,\d+/) { # comma separated number #!!!!!! but commas are removed above ... 
    108205                my $wordnum = num2en($number); 
    109206                $wordnum =~ s/-/ /g; # dash - compound number            
    …… 
    112209                        push (@$words, uc $word); 
    113210                } 
    114                 print "converted number:$number: to $wordnum\n"; 
     211                print "info: converted number:$number: to $wordnum\n"; 
    115212        } elsif (($number =~ /^\d{4}$/) and ($number < 2100)){ # assume 4 digit numbers between 1000 and 2100 are years 
    116213                my $datenum = year2en($number); 
    …… 
    120217                        push (@$words, uc $word); 
    121218                }        
    122                 print "converted date:$number: to $datenum\n";         
     219                print "info: converted date:$number: to $datenum\n";   
    123220        } elsif ($number =~ /^\d+$/) { # contains only numbers 
    124221                my $wordnum = num2en($number); 
    …… 
    128225                        push (@$words, uc $word); 
    129226                } 
    130                 print "converted number:$number: to $wordnum\n"; 
     227                print "info: converted number:$number: to $wordnum\n"; 
    131228        } elsif ($number =~ /^£\d+/) { # convert pounds to words 
    132229                $number =~ s/^£//; # remove pound sign 
    …… 
    138235                } 
    139236                push (@$words, "POUNDS"); 
    140                 print "converted pounds:£$number: to $wordnum pounds\n"; 
     237                print "info: converted pounds:£$number: to $wordnum pounds\n"; 
    141238        } elsif ($number =~ /^\$\d+/) { # convert dollars to words 
    142239                $number =~ s/^\$//; # remove dollar sign 
    …… 
    148245                } 
    149246                push (@$words, "DOLLARS"); 
    150                 print "converted dollars:$number: to $wordnum dollars\n"; 
     247                print "info: converted dollars:$number: to $wordnum dollars\n"; 
    151248# skip this - minutes do not get processed properly (since they use a signle quote) - do manually in eText file.                 
    152249#       } elsif ($number =~ /^\d{1,3}°$/) { # convert degrees to words 
    …… 
    169266                        push (@$words, uc $word); 
    170267                } 
    171                 print "converted number:$number: to $wordnum \n"; 
     268                print "info: converted number:$number: to $wordnum \n"; 
     269        } elsif ($number =~ /^\w+\d+/) { # convert ordinal number to words 
     270                my $numbertemp = $number; 
     271                $numbertemp =~ s/\D+//; # remove nondigit character 
     272                my $wordnum = num2en_ordinal($numbertemp); 
     273                $wordnum =~ s/-/ /g; # dash - compound number                    
     274                my @wordnumlist = split(/ /,$wordnum); 
     275                foreach my $word (@wordnumlist) { 
     276                        push (@$words, uc $word); 
     277                } 
     278                print "info: converted number:$number: to $wordnum \n"; 
    172279        } else { 
    173280                push (@$words, $number); 
    174                 print "****$number not converted\n"; 
     281                confess "error $number not converted\n"; 
    175282        } 
    176283                 

  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook/interim_files/aligned.out

    r2578 r2585  
    11#!MLF!# 
    22"*/downsampled.rec" 
    3 0 25000000 sil -12504.145508 SENT-END 
    4 25000000 26600000 dh -1063.311646 THOSE 
    5 26600000 28700000 ow -1322.120972 
    6 28700000 30000000 z -869.062622 
    7 30000000 30000000 sp -0.235017 
    8 30000000 31400000 iy -905.131226 EVENING 
    9 31400000 32000000 v -374.610107 
    10 32000000 32900000 n -586.843201 
    11 32900000 33300000 ix -266.860107 
    12 33300000 35000000 ng -1051.927002 
    13 35000000 35000000 sp -0.235017 
    14 35000000 35600000 b -387.685791 BELLS 
    15 35600000 37000000 eh -882.883545 
    16 37000000 39400000 l -1523.278320 
    17 39400000 41100000 z -1123.562622 
    18 41100000 42200000 sp -636.472717 
    19 42200000 42500000 b -212.382492 BY 
    20 42500000 43800000 ay -892.630249 
    21 43800000 43800000 sp -0.235017 
    22 43800000 45000000 t -788.817322 THOMAS 
    23 45000000 47400000 aa -1437.506592 
    24 47400000 48200000 m -512.194336 
    25 48200000 48600000 ax -273.034210 
    26 48600000 50100000 s -1051.293213 
    27 50100000 50100000 sp -0.235017 
    28 50100000 51400000 m -876.319092 MOORE 
    29 51400000 53600000 uh -1355.980347 
    30 53600000 55300000 r -1143.363525 
    31 55300000 60200000 sp -2658.927002 
    32 60200000 62000000 r -1157.041748 READ 
    33 62000000 63200000 eh -767.579407 
    34 63200000 64300000 d -697.032410 
    35 64300000 64300000 sp -0.235017 
    36 64300000 65800000 f -859.398987 FOR 
    37 65800000 68200000 ao -1561.661621 
    38 68200000 70300000 r -1418.653687 
    39 70300000 70300000 sp -0.235017 
    40 70300000 72300000 m -1382.702515 MOJOMOVE411 
    41 72300000 73900000 ow -978.509583 
    42 73900000 74800000 jh -591.590271 
    43 74800000 76500000 ow -1101.388306 
    44 76500000 77700000 m -697.787048 
    45 77700000 80600000 uw -1760.078613 
    46 80600000 82600000 v -1403.530029 
    47 82600000 84400000 f -1091.546265 
    48 84400000 87700000 n -2531.834717 
    49 87700000 90500000 n -1852.228149 
    50 90500000 90500000 sp -0.235017 
    51 90500000 90800000 k -240.841125 COM 
    52 90800000 92600000 aa -1081.417236 
    53 92600000 94900000 m -1386.785156 
    54 94900000 94900000 sp -0.235017 
    55 94900000 95900000 b -623.744507 BY 
    56 95900000 103700000 ay -5017.617676 
    57 103700000 106800000 sp -1927.296143 
    58 106800000 110000000 r -2306.654541 ROBERT 
    59 110000000 111200000 aa -703.356628 
    60 111200000 112000000 b -572.268555 
    61 112000000 113200000 er -802.027893 
    62 113200000 113800000 t -399.493500 
    63 113800000 113800000 sp -0.235017 
    64 113800000 115300000 s -973.368225 SCOTT 
    65 115300000 115800000 k -346.667633 
    66 115800000 118600000 aa -1652.790161 
    67 118600000 118900000 t -217.191360 
    68 118900000 127100000 sp -4432.108887 
    69 127100000 128500000 ae -927.945312 AS 
    70 128500000 129700000 z -794.615784 
    71 129700000 129700000 sp -0.235017 
    72 129700000 130800000 p -681.060791 PART 
    73 130800000 131700000 aa -618.721863 
    74 131700000 132800000 r -771.861633 
    75 132800000 133100000 t -219.589584 
    76 133100000 133100000 sp -0.235017 
    77 133100000 133400000 ah -194.171768 OF 
    78 133400000 134500000 v -638.761475 
    79 134500000 134500000 sp -0.235017 
    80 134500000 134900000 dh -256.203461 THE 
    81 134900000 135400000 ax -328.101715 
    82 135400000 135400000 sp -0.235017 
    83 135400000 136400000 v -622.797791 VOXFORGE 
    84 136400000 138500000 aa -1219.480103 
    85 138500000 139400000 k -650.145081 
    86 139400000 140600000 s -741.079590 
    87 140600000 141100000 f -317.815033 
    88 141100000 142300000 ao -810.766357 
    89 142300000 144000000 r -1171.934448 
    90 144000000 145800000 jh -1243.679077 
    91 145800000 145800000 sp -0.235017 
    92 145800000 151700000 ao -4049.692871 ORG 
    93 151700000 153700000 r -1328.250610 
    94 153700000 154300000 g -424.893402 
    95 154300000 158300000 sp -2182.887939 
    96 158300000 160600000 sh -1436.213013 SHORTS 
    97 160600000 162000000 ao -967.496826 
    98 162000000 163200000 r -828.032471 
    99 163200000 163700000 t -335.383789 
    100 163700000 165800000 s -1386.576294 
    101 165800000 166600000 sp -441.940674 
    102 166600000 168700000 w -1360.698730 WEEKLY 
    103 168700000 170200000 iy -1012.960938 
    104 170200000 170700000 k -369.333679 
    105 170700000 171600000 l -659.565674 
    106 171600000 172600000 iy -665.369934 
    107 172600000 172600000 sp -0.235017 
    108 172600000 173000000 m -250.922897 MONOLOGUE 
    109 173000000 175400000 aa -1489.473389 
    110 175400000 175700000 n -242.715103 
    111 175700000 176000000 ax -221.046005 
    112 176000000 176300000 l -215.975601 
    113 176300000 176600000 ao -229.448303 
    114 176600000 181000000 g -3165.420654 
    115 181000000 182300000 sp -695.738953 
    116 182300000 183300000 k -677.003906 COLLECTION 
    117 183300000 184000000 ax -455.986847 
    118 184000000 185600000 l -1045.381714 
    119 185600000 186200000 eh -418.771515 
    120 186200000 187100000 k -615.256592 
    121 187100000 188300000 sh -724.127808 
    122 188300000 188700000 ax -257.210266 
    123 188700000 189700000 n -626.877502 
    124 189700000 219600000 sp -15811.746094 
    125 219600000 220900000 dh -852.003235 THOSE 
    126 220900000 222900000 ow -1237.770264 
    127 222900000 224100000 z -853.892212 
    128 224100000 224100000 sp -0.235017 
    129 224100000 225600000 iy -974.090637 EVENING 
    130 225600000 226100000 v -306.154053 
    131 226100000 226900000 n -529.811523 
    132 226900000 227400000 ix -325.192169 
    133 227400000 228900000 ng -916.310974 
    134 228900000 228900000 sp -0.235017 
    135 228900000 229300000 b -292.913208 BELLS 
    136 229300000 230700000 eh -878.266785 
    137 230700000 233000000 l -1477.806763 
    138 233000000 235100000 z -1372.717896 
    139 235100000 235100000 sp -0.235017 
    140 235100000 237000000 dh -1251.036621 THOSE 
    141 237000000 238900000 ow -1176.476685 
    142 238900000 240100000 z -808.065613 
    143 240100000 240100000 sp -0.235017 
    144 240100000 241800000 iy -1051.050415 EVENING 
    145 241800000 242200000 v -237.337112 
    146 242200000 243100000 n -561.080078 
    147 243100000 243600000 ix -324.897034 
    148 243600000 245200000 ng -928.994263 
    149 245200000 245200000 sp -0.235017 
    150 245200000 245600000 b -269.382111 BELLS 
    151 245600000 247000000 eh -882.679077 
    152 247000000 249400000 l -1534.862549 
    153 249400000 251000000 z -999.659790 
    154 251000000 252400000 sp -810.360474 
    155 252400000 252700000 dh -191.927155 THOSE 
    156 252700000 254300000 ow -1005.157776 
    157 254300000 254600000 z -249.030563 
    158 254600000 254600000 sp -0.235017 
    159 254600000 254900000 iy -233.816315 EVENING 
    160 254900000 255200000 v -248.230988 
    161 255200000 255800000 n -406.460815 
    162 255800000 258700000 ix -1827.929199 
    163 258700000 259000000 ng -201.385193 
    164 259000000 259000000 sp -0.235017 
    165 259000000 259300000 b -203.654861 BELLS 
    166 259300000 262100000 eh -1718.569336 
    167 262100000 262600000 l -365.826385 
    168 262600000 262900000 z -224.563644 
    169 262900000 262900000 sp -0.235017 
    170 262900000 263200000 hh -213.729538 HOW 
    171 263200000 264000000 aw -514.845581 
    172 264000000 264000000 sp -0.235017 
    173 264000000 264300000 m -196.316437 MANY 
    174 264300000 264600000 eh -209.032455 
    175 264600000 265000000 n -255.899612 
    176 265000000 265400000 iy -278.018890 
    177 265400000 265400000 sp -0.235017 
    178 265400000 266000000 ax -394.383759 A 
    179 266000000 266000000 sp -0.235017 
    180 266000000 266300000 t -214.197128 TALE 
    181 266300000 266600000 ey -219.312790 
    182 266600000 266900000 l -233.756607 
    183 266900000 266900000 sp -0.235017 
    184 266900000 267200000 dh -243.673233 THEIR 
    185 267200000 267500000 eh -275.131104 
    186 267500000 267800000 r -209.015839 
    187 267800000 267800000 sp -0.235017 
    188 267800000 268400000 m -354.742706 MUSIC 
    189 268400000 269600000 y -715.677551 
    190 269600000 270000000 uw -266.001984 
    191 270000000 271100000 z -717.290710 
    192 271100000 271800000 ix -453.763885 
    193 271800000 272200000 k -282.080200 
    194 272200000 273000000 sp -470.275146 
    195 273000000 274000000 t -657.040100 TELLS 
    196 274000000 275300000 eh -835.404663 
    197 275300000 277400000 l -1320.569702 
    198 277400000 279000000 z -985.225159 
    199 279000000 283500000 sp -2486.716064 
    200 283500000 284600000 ah -750.905518 OF 
    201 284600000 285500000 v -541.886108 
    202 285500000 285500000 sp -0.235017 
    203 285500000 287600000 y -1273.396240 YOUTH 
    204 287600000 288400000 uw -577.244629 
    205 288400000 289500000 th -723.678772 
    206 289500000 289500000 sp -0.235017 
    207 289500000 291200000 ae -1046.697388 AND 
    208 291200000 292400000 n -748.245056 
    209 292400000 292700000 d -214.433289 
    210 292700000 293000000 sp -200.961472 
    211 293000000 293400000 hh -284.731720 HOME 
    212 293400000 296800000 ow -2006.148438 
    213 296800000 298700000 m -1156.006592 
    214 298700000 299300000 sp -363.830475 
    215 299300000 300800000 ae -910.493347 AND 
    216 300800000 301700000 n -558.467163 
    217 301700000 302000000 d -213.420975 
    218 302000000 302200000 sp -130.064911 
    219 302200000 302700000 dh -349.395111 THAT 
    220 302700000 304400000 ae -1032.012329 
    221 304400000 304700000 t -217.941757 
    222 304700000 304900000 sp -135.911072 
    223 304900000 306800000 s -1303.848389 SWEET 
    224 306800000 307700000 w -592.553345 
    225 307700000 309100000 iy -904.467529 
    226 309100000 309400000 t -199.427887 
    227 309400000 310400000 sp -554.509521 
    228 310400000 311100000 t -465.579773 TIME 
    229 311100000 314800000 ay -2086.032227 
    230 314800000 316200000 m -892.458313 
    231 316200000 319900000 sp -2175.653076 
    232 319900000 321000000 w -772.708069 WHEN 
    233 321000000 321300000 eh -198.406158 
    234 321300000 322300000 n -625.902100 
    235 322300000 322300000 sp -0.235017 
    236 322300000 323600000 l -847.156067 LAST 
    237 323600000 325100000 ae -863.897278 
    238 325100000 326300000 s -783.176392 
    239 326300000 326600000 t -246.635986 
    240 326600000 326600000 sp -0.235017 
    241 326600000 328500000 ay -1189.687622 I 
    242 328500000 328500000 sp -0.235017 
    243 328500000 329000000 hh -343.691681 HEARD 
    244 329000000 333000000 er -2478.330078 
    245 333000000 333700000 d -499.631836 
    246 333700000 334700000 sp -597.968140 
    247 334700000 336000000 dh -827.133789 THEIR 
    248 336000000 336800000 eh -510.939667 
    249 336800000 337600000 r -551.281006 
    250 337600000 337600000 sp -0.235017 
    251 337600000 339700000 s -1374.088501 SOOTHING 
    252 339700000 341400000 uw -1030.686890 
    253 341400000 341800000 dh -261.625519 
    254 341800000 342700000 ix -569.829651 
    255 342700000 344100000 ng -840.131226 
    256 344100000 344100000 sp -0.235017 
    257 344100000 345400000 ch -817.539368 CHIME 
    258 345400000 348600000 ay -1862.573853 
    259 348600000 349700000 m -652.768433 
    260 349700000 361000000 sp -6156.908691 
    261 361000000 361400000 dh -263.359253 THOSE 
    262 361400000 362900000 ow -934.279602 
    263 362900000 364200000 z -906.128662 
    264 364200000 364200000 sp -0.235017 
    265 364200000 365200000 jh -701.320068 JOYOUS 
    266 365200000 367800000 oy -1655.157593 
    267 367800000 368200000 ax -284.341492 
    268 368200000 369500000 s -825.133789 
    269 369500000 369500000 sp -0.235017 
    270 369500000 372300000 aw -1613.715088 HOURS 
    271 372300000 374000000 er -1157.235229 
    272 374000000 375200000 z -785.704590 
    273 375200000 375200000 sp -0.235017 
    274 375200000 376500000 aa -912.884399 ARE 
    275 376500000 377900000 r -976.369202 
    276 377900000 378100000 sp -124.798691 
    277 378100000 378900000 p -566.831360 PASSED 
    278 378900000 380800000 ae -1155.449341 
    279 380800000 382100000 s -789.475403 
    280 382100000 382400000 t -213.975235 
    281 382400000 382400000 sp -0.235017 
    282 382400000 382900000 ax -341.890259 AWAY 
    283 382900000 385100000 w -1423.813110 
    284 385100000 387700000 ey -1710.973755 
    285 387700000 393200000 sp -3026.807373 
    286 393200000 394700000 ae -932.186279 AND 
    287 394700000 395700000 n -620.766174 
    288 395700000 396000000 d -194.880798 
    289 396000000 396000000 sp -0.235017 
    290 396000000 397400000 m -902.758545 MANY 
    291 397400000 398400000 eh -574.389038 
    292 398400000 398900000 n -310.895477 
    293 398900000 400000000 iy -690.868713 
    294 400000000 400000000 sp -0.235017 
    295 400000000 400600000 ax -425.777039 A 
    296 400600000 400600000 sp -0.235017 
    297 400600000 401400000 hh -542.003906 HEART 
    298 401400000 403100000 aa -1107.815918 
    299 403100000 405100000 r -1393.089966 
    300 405100000 405400000 t -198.724930 
    301 405400000 406500000 sp -604.077515 
    302 406500000 408000000 dh -986.753601 THAT 
    303 408000000 409300000 ae -792.031555 
    304 409300000 409700000 t -281.396667 
    305 409700000 409700000 sp -0.235017 
    306 409700000 410900000 dh -750.968994 THEN 
    307 410900000 412500000 eh -942.301880 
    308 412500000 414300000 n -1076.298218 
    309 414300000 414300000 sp -0.235017 
    310 414300000 414900000 w -360.840729 WAS 
    311 414900000 415200000 aa -250.579025 
    312 415200000 416600000 z -923.695618 
    313 416600000 416600000 sp -0.235017 
    314 416600000 417000000 g -280.140259 GAY 
    315 417000000 421700000 ey -3020.978760 
    316 421700000 425800000 sp -2353.206543 
    317 425800000 426700000 w -608.577942 WITHIN 
    318 426700000 427100000 ix -290.349762 
    319 427100000 427900000 dh -515.343750 
    320 427900000 429000000 ih -667.862122 
    321 429000000 430400000 n -839.669983 
    322 430400000 430400000 sp -0.235017 
    323 430400000 430700000 dh -193.130203 THE 
    324 430700000 431300000 ax -377.960571 
    325 431300000 431300000 sp -0.235017 
    326 431300000 433000000 t -1116.695679 TOMB 
    327 433000000 433700000 uw -442.870117 
    328 433700000 437800000 m -2455.729004 
    329 437800000 438000000 sp -126.176971 
    330 438000000 439400000 n -831.124573 NOW 
    331 439400000 441000000 aw -950.480530 
    332 441000000 441000000 sp -0.235017 
    333 441000000 442200000 d -776.556152 DARKLY 
    334 442200000 443000000 aa -547.418640 
    335 443000000 444700000 r -1168.941406 
    336 444700000 445000000 k -203.224365 
    337 445000000 446100000 l -762.129700 
    338 446100000 446700000 iy -436.763824 
    339 446700000 446700000 sp -0.235017 
    340 446700000 447900000 d -768.778198 DWELLS 
    341 447900000 449200000 w -860.453308 
    342 449200000 450100000 eh -581.315430 
    343 450100000 452000000 l -1182.789429 
    344 452000000 453500000 z -926.071228 
    345 453500000 456900000 sp -1975.332764 
    346 456900000 457900000 ae -665.382690 AND 
    347 457900000 458800000 n -577.460999 
    348 458800000 459500000 d -471.043732 
     30 12000000 sil -5673.811523 SENT-END 
     412000000 12700000 w -417.862579 WHEN 
     512700000 13300000 eh -347.555664 
     613300000 14600000 n -743.281616 
     714600000 14600000 sp -0.235017 
     814600000 14900000 dh -194.959946 THE 
     914900000 15300000 ax -238.537292 
     1015300000 15300000 sp -0.235017 
     1115300000 16900000 s -954.239319 SUNLIGHT 
     1216900000 17900000 ah -595.353027 
     1317900000 18800000 n -548.593445 
     1418800000 19100000 l -202.643707 
     1519100000 20200000 ay -687.100037 
     1620200000 20800000 t -412.797913 
     1720800000 20800000 sp -0.235017 
     1820800000 22400000 s -993.840881 STRIKES 
     1922400000 22800000 t -263.954926 
     2022800000 23500000 r -437.177673 
     2123500000 24900000 ay -842.782837 
     2224900000 25700000 k -548.693726 
     2325700000 26900000 s -756.550354 
     2426900000 32600000 sp -3288.146484 
     2532600000 32900000 r -203.561249 RAINDROPS 
     2632900000 33200000 ey -192.660385 
     2733200000 33500000 n -195.546982 
     2833500000 33800000 d -188.092819 
     2933800000 34300000 r -340.222931 
     3034300000 35200000 aa -576.858521 
     3135200000 36000000 p -513.172607 
     3236000000 37300000 s -757.558289 
     3337300000 37500000 sp -118.239151 
     3437500000 38000000 ix -289.680725 IN 
     3538000000 38700000 n -418.201782 
     3638700000 38700000 sp -0.235017 
     3738700000 39000000 dh -201.682281 THE 
     3839000000 40400000 ax -839.995483 
     3940400000 40400000 sp -0.235017 
     4040400000 42300000 eh -1102.145142 AIR 
     4142300000 42800000 r -326.643799 
     4242800000 43400000 sp -338.905640 
     4343400000 44200000 dh -528.523987 THEY 
     4444200000 44500000 ey -187.813309 
     4544500000 48900000 sp -2331.569824 
     4648900000 52400000 ae -2167.157227 ACT 
     4752400000 53400000 k -696.953003 
     4853400000 53800000 t -291.110931 
     4953800000 53800000 sp -0.235017 
     5053800000 54100000 ae -222.647598 AS 
     5154100000 54700000 z -380.766602 
     5254700000 54700000 sp -0.235017 
     5354700000 55200000 ax -322.413544 A 
     5455200000 55200000 sp -0.235017 
     5555200000 56200000 p -611.651917 PRISM 
     5656200000 56900000 r -489.490723 
     5756900000 57400000 ih -317.594421 
     5857400000 58200000 z -513.132385 
     5958200000 58900000 ax -431.784210 
     6058900000 60100000 m -643.696655 
     6160100000 60100000 sp -0.235017 
     6260100000 60400000 ae -180.548752 AND 
     6360400000 61000000 n -372.154572 
     6461000000 61300000 d -188.439804 
     6561300000 62500000 sp -645.124695 
     6662500000 62800000 f -201.630539 FORM 
     6762800000 63700000 ao -511.759155 
     6863700000 64000000 r -209.089828 
     6964000000 64600000 m -348.604187 
     7064600000 64600000 sp -0.235017 
     7164600000 65300000 ax -436.575226 A 
     7265300000 65300000 sp -0.235017 
     7365300000 66200000 r -563.504333 RAINBOW 
     7466200000 66800000 ey -354.545532 
     7566800000 67700000 n -534.946655 
     7667700000 68000000 b -188.959869 
     7768000000 69300000 ow -766.216187 
     7869300000 77400000 sp -4230.157715 
     7977400000 77700000 dh -186.641479 THE 
     8077700000 78000000 ax -195.928680 
     8178000000 78000000 sp -0.235017 
     8278000000 78600000 r -386.282410 RAINBOW 
     8378600000 79300000 ey -423.097778 
     8479300000 80100000 n