voxforge.org
VoxForge Dev
Show
Ignore:
Timestamp:
05/29/08 23:01:55 (6 months ago)
Author:
kmaclean
Message:

AudioSegmentation scripts - Sequitor G2P pronunciation alternatives validation to Audio using HVite Forced Alignment - snapshot

Files:

Legend:

Unmodified
Added
Removed
Modified
Copied
Moved
  • Trunk/Scripts/Audio_scripts/AudioSegmentation/AudioBook/output_files/AudioBook_Log

    r2595 r2597  
    33Changes made to Text file 
    44------------------------- 
    5 converted number:18: to eighteen 
    6 converted number:89: to eighty nine 
    7 converted date:1830: to eighteen thirty 
    8 converted date:1844: to eighteen forty four 
    9 converted date:1859: to eighteen fifty nine 
    10 converted date:1837: to eighteen thirty seven 
    11 converted date:1836: to eighteen thirty six 
     5changed URL MOJOMOVE411.COM to:MOJOMOVE411 DOT COM; 
     6converted number:4: to four 
     7converted number:1: to one 
     8converted number:1: to one 
     9changed URL VOXFORGE.ORG to:VOXFORGE DOT ORG; 
    1210 
    1311Words with period (".") removed from body of word - please review: 
     
    1614Words with single quotes (no change made to word, unless otherwise stated) - please review: 
    1715------------------------------------------------------------------------------------------- 
    18 changed:'FORCE to:FORCE 
    19 changed:'ATTRACTIVE' to:ATTRACTIVE 
    20 changed:'REPULSIVE' to:REPULSIVE 
    21 changed:'FORCE' to:FORCE 
    22 changed:'ATTRACTIVE to:ATTRACTIVE 
    23 changed:FORCES' to:FORCES 
    24 changed:'FORCES' to:FORCES 
    25 changed:'ATTRACTIVE to:ATTRACTIVE 
    26 changed:FORCES' to:FORCES 
    27 changed:'FORCE' to:FORCE 
    28 changed:'ATTRACTION to:ATTRACTION 
    29 changed:'THE to:THE 
    30 changed:'LAWS to:LAWS 
    31 changed:'CHAOS' to:CHAOS 
    32 changed:'NEBULAR to:NEBULAR 
    33 changed:'PROTOGAEA' to:PROTOGAEA 
    34 changed:'THEORIE to:THEORIE 
    35 changed:'THE to:THE 
    36 DARWIN'S 
    37 changed:'ORIGIN to:ORIGIN 
    38 changed:SPECIES' to:SPECIES 
    39 changed:'PHILOSOPHIE to:PHILOSOPHIE 
    40 changed:ZOOLOGIQUE' to:ZOOLOGIQUE 
    41 DARWIN'S 
    42 changed:'PROGRESSIVE to:PROGRESSIVE 
    43 changed:TRANSMUTATION' to:TRANSMUTATION 
    44 changed:'DEVELOPMENT' to:DEVELOPMENT 
    45 changed:'ORIGIN to:ORIGIN 
    46 changed:'SYNTHETIC to:SYNTHETIC 
    47 changed:PHILOSOPHY' to:PHILOSOPHY 
    48 changed:'PHILOSOPHIC to:PHILOSOPHIC 
    49 changed:POSITIVE' to:POSITIVE 
    50 SPENCER'S 
    51 changed:'IGNORAMUS to:IGNORAMUS 
     16changed:'T to:T 
    5217 
    5318Missing Words that need to be added to Pronunciation Dictionary, with suggested pronunciations: 
    5419----------------------------------------------------------------------------------------------- 
    55 APPERTAIN       [APPERTAIN]     ae p er t ax n 
    56 ASCRIBING       [ASCRIBING]     ax s k r ay b ix ng 
    57 BANEFUL         [BANEFUL]       b ax n f ax l 
    58 BUFFON          [BUFFON]        b uw f ow n 
    59 CATASTROPHISM   [CATASTROPHISM] k ax t ae s t r ax f ih z ax m 
    60 CAUSA           [CAUSA]         k aa z ax 
    61 COMTE           [COMTE]         k aa m t 
    62 CORPUSCLES      [CORPUSCLES]    k ao r p ah s k ax l z 
    63 DARWIN'S        [DARWIN'S]      d aa r w ix n z 
    64 DUNAMIS         [DUNAMIS]       d uw n aa m iy z 
    65 EFFACED         [EFFACED]       ix f ey s t 
    66 ELUCIDATION     [ELUCIDATION]   ix l uw s ax d ey sh ax n 
    67 EMANISTIC       [EMANISTIC]     eh m ax n ih s t ix k 
    68 ENERGEIA        [ENERGEIA]      eh n er jh ey ax 
    69 EXPLICABLE      [EXPLICABLE]    ix k s p l ih s ax b ax l 
    70 FERTILISATION   [FERTILISATION] f er dx ax l ix z ey sh ax n 
    71 FIXITY          [FIXITY]        f ih k s ax dx iy 
    72 FORMLESS        [FORMLESS]      f ao r m l ax s 
    73 FRAUNHOFER      [FRAUNHOFER]    f r ao n hh ax f er 
    74 GALVANO         [GALVANO]       g aa l v aa n ow 
    75 GNOSTIC         [GNOSTIC]       n aa s t ix k 
    76 HILAIRE         [HILAIRE]       hh ix l ey r 
    77 IGNORABIMUS     [IGNORABIMUS]   ih g n er ax b ay m ax s 
    78 IMAGINABLY      [IMAGINABLY]    ix m ae jh ax n ax b l iy 
    79 INQUIRERS       [INQUIRERS]     ix n k w ay er er z 
    80 INTERMEDIATION [INTERMEDIATION] ih n t er m iy dx iy ey sh ax n 
    81 INVOLUTION      [INVOLUTION]    ih n v ax l uw sh ax n 
    82 IONIAN          [IONIAN]        ay ow n iy ax n 
    83 IRREFRAGABLE    [IRREFRAGABLE]  ix r ax f r aa g ax b ax l 
    84 LEVELLING       [LEVELLING]     l eh v ax l ix ng 
    85 MAGNETO         [MAGNETO]       m ae g n eh dx ow 
    86 MINUTENESS      [MINUTENESS]    m ih n ax t n ax s 
    87 NEBULAE         [NEBULAE]       n eh b y ax l ey 
    88 NEBULAR         [NEBULAR]       n eh b y ax l er 
    89 NEUTRALISED     [NEUTRALISED]   n uw t r ax l ay z d 
    90 PALAETIOLOGICAL [PALAETIOLOGICAL] p ax l ey dx iy ax l aa jh ix k ax l 
    91 POTENTIALITY    [POTENTIALITY]  p ax t eh n sh iy ae l ax dx i 
    92 POULETT         [POULETT]       p uw l eh t 
    93 PRACTICABILITY [PRACTICABILITY] p r ae k t ax k ax b ih l ix dx iy 
    94 PROTOGAEA       [PROTOGAEA]     p r ow dx ax g iy ax 
    95 PUTREFYING      [PUTREFYING]    p y uw t r ax f ay ix ng 
    96 RADIOMETER      [RADIOMETER]    r ey dx iy aa m ix dx er 
    97 REASONINGS      [REASONINGS]    r iy z ax n ix ng z 
    98 RECTILINEAR     [RECTILINEAR]   r eh k t ix l ih n iy er 
    99 REPULSION       [REPULSION]     r iy p ah l sh ax n 
    100 SCROPE          [SCROPE]        s k r ow p 
    101 SPECTROSCOPIC   [SPECTROSCOPIC] s p eh k t r ax s k aa p ix k 
    102 STATICS         [STATICS]       s t ae dx ix k s 
    103 TELEGRAPHY      [TELEGRAPHY]    t eh l ax g r ax f iy 
    104 TELEOLOGY       [TELEOLOGY]     t iy l iy ax l ao jh iy 
    105 THEORIE         [THEORIE]       th ih r iy 
    106 TRANSMUTATION   [TRANSMUTATION] t r ae n s m y uw t ey sh ax n 
    107 TREVIRANUS      [TREVIRANUS]    t r ax v ih r ax n ax s 
    108 VAPORISED       [VAPORISED]     v ey p er ay z d 
    109 ZOOLOGIQUE      [ZOOLOGIQUE]    z ow aa l ax jh iy k 
     20MOJOMOVE        [MOJOMOVE]      m ow jh ow m uw v 
     21VOXFORGE        [VOXFORGE]      v aa k s f ao r jh 
     22 
     23Audio Segmenting summary: 
     24------------------------- 
     25Settings:average sentence length: 15 
     26         target max sentence length: 20 
     27         pause length: 2000000 (0.2 seconds) 
     28 
     29Sentence Length: min:aud0002: 11 
     30                 max:aud0003: 16 
     31 
     32Prompt lines with more than max_sentence_length of 20 words: 
     33        none 
     34Checking for "No tokens survived to final node of network at beam" warnings: 
     35---------------------------------------------------------------------------- 
     36 
     37Top 15 prompts with the lowest average log likelihood per frame 
     38(confirm anything with an avg log likelihood of less than 60): 
     39--------------------------------------------------------------- 
     4056.6717 aud0009 THIS RECORDING IS IN THE PUBLIC DOMAIN 
     4160.3604 aud0004 OF YOUTH AND HOME AND THAT SWEET TIME WHEN LAST I HEARD THEIR SOOTHING CHIME 
     4260.6805 aud0007 AND SO T WILL BE WHEN I AM GONE THAT TUNEFUL PEAL WILL STILL RING ON 
     4360.7166 aud0005 THOSE JOYOUS HOURS ARE PASSED AWAY AND MANY A HEART THAT THEN WAS GAY 
     4460.7951 aud0006 WITHIN THE TOMB NOW DARKLY DWELLS AND HEARS NO MORE THOSE EVENING BELLS 
     4561.2530 aud0008 WHILE OTHER BARDS SHALL WALK THESE DELLS AND SING YOUR PRAISE SWEET EVENING BELLS 
     4661.5115 aud0002 AS PART OF THE VOXFORGE DOT ORG SHORTS WEEKLY MONOLOGUE COLLECTION 
     4761.5859 aud0003 THOSE EVENING BELLS THOSE EVENING BELLS THOSE EVENING BELLS HOW MANY A TALE THEIR MUSIC TELLS 
     4861.6406 aud0001 THOSE EVENING BELLS BY THOMAS MOORE READ FOR MOJOMOVE FOUR ONE ONE DOT COM BY ROBERT SCOTT