nbest-pron-score.1

这是一款很好用的工具包

.\" $Id: nbest-pron-score.1,v 1.5 2004/12/03 17:59:01 stolcke Exp $
.TH nbest-pron-score 1 "$Date: 2004/12/03 17:59:01 $" "SRILM Tools"
.SH NAME
nbest-pron-score \- score pronunciations and pauses in N-best hypotheses
.SH SYNOPSIS
.B nbest-pron-score
[\c
.BR \-help ]
.I option
\&...
.SH DESCRIPTION
.B nbest-pron-score
reads N-best lists and computes log probability scores for the pronunciations
and pauses contained in them.
Pronunciation scoring requires that the N-best lists
contain phone backtraces in "NBestList2.0"
.BR nbest-format (5).
.PP
Pronunciation scores are computed from the probabilities in a dictionary.
Pauses are binned into three length classes (none, short, long) and 
scored according to a trigram language model that conditions the pause length
on the left and right neighboring words, in that order (so that bigram
backoff uses the left neighbor only).
.SH OPTIONS
.PP
Each filename argument can be an ASCII file, or a 
compressed file (name ending in .Z or .gz), or ``-'' to indicate
stdin/stdout.
.TP
.B \-help
Print option summary.
.TP
.B \-version
Print version information.
.TP
.BI \-debug " level"
Controls the amount of output (the higher the
.IR level ,
the more).
.TP
.B \-tolower
Map all vocabulary to lowercase.
Useful if case conventions for text/counts and language model differ.
.TP
.B \-multiwords
Deal with N-best lists containing multiwords joined by underscores.
This only affects pause scoring: if a word adjacent to a pause is 
a multiword and is not in the vocabulary of the pause LM, then it is split
and only the component closest to the pause is conditioned on.
.TP
.BI \-nbest " file"
Score the N-best hypothese in 
.IR file .
.TP
.BI \-rescore " file"
Same as 
.BR \-nbest .
.TP
.BI \-nbest-files " file"
Process all N-best list filenames listed in 
.IR file .
.TP
.BI \-max-nbest " n"
Limits the number of hypotheses read from an N-best list.
Only the first
.I n
hypotheses are processed.
.TP
.BI \-dictionary " file"
Enable pronunciation scoring, using the pronunciation dictionary 
.IR file .
Each line contains a pronunciation in the format
.br
	\fIword\fP [\fIp\fP] \fIphone\fP ...
.br
The optional value 
.I p
is the pronunciation probability.
If the second field in a line is not a number the pronunciation is assumed
to have probability one.
.TP
.B \-intlogs
Interpret probabilities in the dictionary as intlog-scaled log probabilities
(as used in the SRI Decipher(TM) system), rather than straight probabilities.
.TP
.BI \-pause-lm " file"
Enable pause scoring, using the pause LM in
.IR file .
.TP
.BI \-no-pause " tag"
The word used to represent the absence of a pause in the pause LM.
.TP
.BI \-short-pause " tag"
The word used to represent a short pause in the pause LM.
.TP
.BI \-long-pause " tag"
The word used to represent a long pause in the pause LM.
.TP
.BI \-min-pause-dur " T"
The minimum duration, in seconds, for a non-speech region to be considered
a (short) pause.
.TP
.BI \-long-pause-dur " T"
The duration, in second, above which a non-speech region is considered a
"long" pause.
.PP
The default values for pause tags and duration thresholds are printed by the
.B \-help
option.
.TP
.BI \-pron-score-dir " dir"
Write pronunciation scores to
.IR dir 
when processing multiple N-best lists,
using output filenames derived from the input files.
.TP
.BI \-pause-score-dir " dir"
Write pause scores to
.IR dir 
when processing multiple N-best lists,
using output filenames derived from the input files.
.TP
.BI \-pause-score-weight " W"
Add pause LM scores to the pronunciation scores after multiplying them
by 
.IR W .
This creates a single weighted combination of both models.
Pause scores can still be output separately by specifying 
.BR \-pause-score-dir .
.SH "SEE ALSO"
nbest-format(5), nbest-scripts(1), nbest-optimize(1), ngram(1).
.br
D. Vergyri, A. Stolcke, V. R. R. Gadde, L. Ferrer, & E. Shriberg,
``Prosodic Knowledge Sources for Automatic Speech Recognition''.
\fIProc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing\fP,
Hong Kong, April 2003.
.SH BUGS
The binning of pause lengths into three classes should be generalized.
.SH AUTHOR
Andreas Stolcke <[e-mail]>.
.br
Copyright 2002\-2004 SRI International