wlat-format.5

这是一款很好用的工具包

wlat-format(5)                                     wlat-format(5)



NNAAMMEE
       wlat-format  -  File  format for SRILM word posterior lat-
       tices

SSYYNNOOPPSSIISS
       Word lattices:
       vveerrssiioonn 22
       nnaammee _s
       iinniittiiaall _i
       ffiinnaall _f
       nnooddee _n _w _a _p _n_1 _p_1 _n_2 _p_2 ...
       ...
       Word meshes (confusion networks):
       nnaammee _s
       nnuummaalliiggnnss _N
       ppoosstteerriioorr _P
       aalliiggnn _a _w_1 _p_1 _w_2 _p_2 ...
       rreeffeerreennccee _a _w
       hhyyppss _a _w _h_1 _h_2 ...
       iinnffoo _a _w _s_t_a_r_t _d_u_r _a_s_c_o_r_e _g_s_c_o_r_e _p_h_o_n_e_s _p_h_o_n_e_d_u_r_s
       ...

DDEESSCCRRIIPPTTIIOONN
       Word posterior lattices and meshes are lattices  generated
       by aligning N-best hypotheses with nnbbeesstt--llaattttiiccee(1), or by
       aligning PFSG or HTK lattices with llaattttiiccee--ttooooll(1).   They
       compactly  encode  possible  word hypotheses sequences and
       their posterior probabilities.  (Word meshes  have  become
       generally    known    as    ``confusion    networks''   or
       ``sausages.'')

       A word lattice is a partially ordered directed graph  with
       nodes  representing word hypotheses.  Nodes are identified
       by non-negative integers.  The file format  specifies  the
       initial  node _i, the final node _f, and any number of addi-
       tional nodes _n.  For each node _n the following  associated
       information is given on the same line: the word identity _w
       (the string  ``NULL''  is  used  with  initial  and  final
       nodes), the alignment position _a (identical values in this
       field identify hypotheses that occur  at  the  same  posi-
       tion),  and  the  word posterior probability _p.  Following
       these values, zero or more transitions to successor  nodes
       are  specified,  each  given  by the node index _n_i and the
       transition posterior probability _p_i.  In a  properly  nor-
       malized  word  lattice the transition posteriors _p_i sum up
       to the node posterior _p.

       Word meshes represent a more constrained lattice format in
       which  word  hypotheses are in a total order.  A mesh con-
       tains a number of alignment positions, and a set of  mutu-
       ally  exclusive  word  hypotheses  in  each  position (the
       ``confusion sets'').  The word mesh  represents  all  sen-
       tence hypotheses that can be generated by freely combining
       word hypotheses at each position.  The file format  speci-
       fies  the  number  of  alignment positions _A and the total
       posterior probability mass _P  contained  in  the  lattice,
       followed by one or more confusion set specifications.  For
       each alignment position _a, the hypothesized words  _w_i  and
       their  posterior  probabilities  _p_i are listed in alterna-
       tion.  The pseudo-word string **DDEELLEETTEE** represents an empty
       hypothesis.

       Optionally, the word mesh format encodes additional infor-
       mation  about  the  hypothesis  alignment  from  which  it
       resulted.   The  keyword  rreeffeerreennccee  specifies the correct
       word _w that was aligned at position _a.  The  keyword  hhyyppss
       is used to list the sentence hypotheses of which a certain
       word hypothesis was a part.  The word hypothesis is  iden-
       tified  by  an  alignment postion _a and the word string _w,
       and is followed by the integer IDs _h_i (typically,  the  N-
       best ranks) of the associated sentence hypotheses.

       As  another  optional  element,  the word mesh can contain
       word-level acoustic and  temporal  information,  following
       the  keyword  iinnffoo, the alignment position _a, and the word
       identity _w.  This information  is  derived  by  nnbbeesstt--llaatt--
       ttiiccee(1)  from  word-  and phone-level backtraces of N-best
       hypotheses (as represented in Decipher  NBestList2.0  for-
       mat).   The details of this information are defined in the
       SRILM class NNBBeessttWWoorrddIInnffoo and subject to change, but  cur-
       rently  include the following.  _s_t_a_r_t: word start time (in
       seconds from the beginning of  the  waveform);  _d_u_r:  word
       duration  (in  seconds); _a_s_c_o_r_e: acoustic model likelihood
       (log base 10);  _g_s_c_o_r_e:  grammar  (LM  and  pronunciation)
       score  (log  base  10); _p_h_o_n_e_s: sequence of phones in word
       (separated by colons); _p_h_o_n_e_d_u_r_s: sequence of phone  dura-
       tions  (in  numbers of frames, separated by colons).  When
       word meshes are derived from HTK format lattices,  pronun-
       ciation  field  will  consist  of  the HTK phone alignment
       information, which encodes both phone sequence  and  dura-
       tions;  the phone duration field in turn is used to encode
       the duration model scores, if present.  NNoottee:: The  encoded
       information pertains to the word hypothesis with the high-
       est per-unit-time acoustic score among all  hypotheses  of
       the same word aligned to a given word mesh position.

       Both  formats  optionally  encode the associated utterance
       IDs in the nnaammee field.  Word lattices and  meshes  can  be
       converted to PFSG format using the script wwllaatt--ttoo--ppffssgg.

SSEEEE AALLSSOO
       nbest-lattice(1),  lattice-tool(1), pfsg-scripts(1), pfsg-
       format(5), nbest-format(5).
       L. Mangu, E. Brill, & A. Stolcke, ``Finding  consensus  in
       speech  recognition:  word  error  minimization  and other
       applications of confusion networks,'' _C_o_m_p_u_t_e_r _S_p_e_e_c_h  _a_n_d
       _L_a_n_g_u_a_g_e 14(4), 373-400, 2000.

BBUUGGSS
       Detailed alignment and acoustic information is so far only
       implemented for  word  meshes,  although  conceptually  it
       would apply equally to word lattices.

AAUUTTHHOORR
       Andreas Stolcke <[e-mail]>.
       Copyright 2001-2005 SRI International



SRILM File Formats $Date: 2005/08/22 19:14:08 $    wlat-format(5)