156 lines
5.6 KiB
HTML
156 lines
5.6 KiB
HTML
|
<! $Id: nbest-pron-score.1,v 1.8 2019/09/09 22:35:37 stolcke Exp $>
|
||
|
|
<HTML>
|
||
|
|
<HEADER>
|
||
|
|
<TITLE>nbest-pron-score</TITLE>
|
||
|
|
<BODY>
|
||
|
|
<H1>nbest-pron-score</H1>
|
||
|
|
<H2> NAME </H2>
|
||
|
|
nbest-pron-score - score pronunciations and pauses in N-best hypotheses
|
||
|
|
<H2> SYNOPSIS </H2>
|
||
|
|
<B>nbest-pron-score</B> [ <B>-help</B> ] <I>option</I> ...
|
||
|
|
</PRE>
|
||
|
|
<H2> DESCRIPTION </H2>
|
||
|
|
<B> nbest-pron-score </B>
|
||
|
|
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"
|
||
|
|
<A HREF="nbest-format.5.html">nbest-format(5)</A>.
|
||
|
|
<P>
|
||
|
|
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).
|
||
|
|
<H2> OPTIONS </H2>
|
||
|
|
<P>
|
||
|
|
Each filename argument can be an ASCII file, or a
|
||
|
|
compressed file (name ending in .Z or .gz), or ``-'' to indicate
|
||
|
|
stdin/stdout.
|
||
|
|
<DL>
|
||
|
|
<DT><B> -help </B>
|
||
|
|
<DD>
|
||
|
|
Print option summary.
|
||
|
|
<DT><B> -version </B>
|
||
|
|
<DD>
|
||
|
|
Print version information.
|
||
|
|
<DT><B>-debug</B><I> level</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Controls the amount of output (the higher the
|
||
|
|
<I>level</I>,<I></I><I></I><I></I>
|
||
|
|
the more).
|
||
|
|
<DT><B> -tolower </B>
|
||
|
|
<DD>
|
||
|
|
Map all vocabulary to lowercase.
|
||
|
|
Useful if case conventions for text/counts and language model differ.
|
||
|
|
<DT><B> -multiwords </B>
|
||
|
|
<DD>
|
||
|
|
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.
|
||
|
|
<DT><B>-multi-char</B><I> C</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Character used to delimit component words in multiwords
|
||
|
|
(an underscore character by default).
|
||
|
|
<DT><B>-nbest</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Score the N-best hypothese in
|
||
|
|
<I>file</I>.<I></I><I></I><I></I>
|
||
|
|
<DT><B>-rescore</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Same as
|
||
|
|
<B>-nbest</B>.<B></B><B></B><B></B>
|
||
|
|
<DT><B>-nbest-files</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Process all N-best list filenames listed in
|
||
|
|
<I>file</I>.<I></I><I></I><I></I>
|
||
|
|
<DT><B>-max-nbest</B><I> n</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Limits the number of hypotheses read from an N-best list.
|
||
|
|
Only the first
|
||
|
|
<I> n </I>
|
||
|
|
hypotheses are processed.
|
||
|
|
<DT><B>-dictionary</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Enable pronunciation scoring, using the pronunciation dictionary
|
||
|
|
<I>file</I>.<I></I><I></I><I></I>
|
||
|
|
Each line contains a pronunciation in the format
|
||
|
|
<PRE>
|
||
|
|
<I>word</I> [<I>p</I>] <I>phone</I> ...
|
||
|
|
</PRE>
|
||
|
|
The optional value
|
||
|
|
<I> p </I>
|
||
|
|
is the pronunciation probability.
|
||
|
|
If the second field in a line is not a number the pronunciation is assumed
|
||
|
|
to have probability one.
|
||
|
|
<DT><B> -intlogs </B>
|
||
|
|
<DD>
|
||
|
|
Interpret probabilities in the dictionary as intlog-scaled log probabilities
|
||
|
|
(as used in the SRI Decipher(TM) system), rather than straight probabilities.
|
||
|
|
<DT><B>-pause-lm</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Enable pause scoring, using the pause LM in
|
||
|
|
<I>file</I>.<I></I><I></I><I></I>
|
||
|
|
<DT><B>-no-pause</B><I> tag</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
The word used to represent the absence of a pause in the pause LM.
|
||
|
|
<DT><B>-short-pause</B><I> tag</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
The word used to represent a short pause in the pause LM.
|
||
|
|
<DT><B>-long-pause</B><I> tag</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
The word used to represent a long pause in the pause LM.
|
||
|
|
<DT><B>-min-pause-dur</B><I> T</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
The minimum duration, in seconds, for a non-speech region to be considered
|
||
|
|
a (short) pause.
|
||
|
|
<DT><B>-long-pause-dur</B><I> T</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
The duration, in second, above which a non-speech region is considered a
|
||
|
|
"long" pause.
|
||
|
|
</DD>
|
||
|
|
</DL>
|
||
|
|
<P>
|
||
|
|
The default values for pause tags and duration thresholds are printed by the
|
||
|
|
<B> -help </B>
|
||
|
|
option.
|
||
|
|
<DL>
|
||
|
|
<DT><B>-pron-score-dir</B><I> dir</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Write pronunciation scores to
|
||
|
|
<I>dir</I><I></I><I></I><I></I>
|
||
|
|
when processing multiple N-best lists,
|
||
|
|
using output filenames derived from the input files.
|
||
|
|
<DT><B>-pause-score-dir</B><I> dir</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Write pause scores to
|
||
|
|
<I>dir</I><I></I><I></I><I></I>
|
||
|
|
when processing multiple N-best lists,
|
||
|
|
using output filenames derived from the input files.
|
||
|
|
<DT><B>-pause-score-weight</B><I> W</I><B></B><I></I><B></B><I></I><B></B>
|
||
|
|
<DD>
|
||
|
|
Add pause LM scores to the pronunciation scores after multiplying them
|
||
|
|
by
|
||
|
|
<I>W</I>.<I></I><I></I><I></I>
|
||
|
|
This creates a single weighted combination of both models.
|
||
|
|
Pause scores can still be output separately by specifying
|
||
|
|
<B>-pause-score-dir</B>.<B></B><B></B><B></B>
|
||
|
|
</DD>
|
||
|
|
</DL>
|
||
|
|
<H2> SEE ALSO </H2>
|
||
|
|
<A HREF="nbest-format.5.html">nbest-format(5)</A>, <A HREF="nbest-scripts.1.html">nbest-scripts(1)</A>, <A HREF="nbest-optimize.1.html">nbest-optimize(1)</A>, <A HREF="ngram.1.html">ngram(1)</A>.
|
||
|
|
<BR>
|
||
|
|
D. Vergyri, A. Stolcke, V. R. R. Gadde, L. Ferrer, & E. Shriberg,
|
||
|
|
``Prosodic Knowledge Sources for Automatic Speech Recognition''.
|
||
|
|
<I>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing</I>,
|
||
|
|
Hong Kong, April 2003.
|
||
|
|
<H2> BUGS </H2>
|
||
|
|
The binning of pause lengths into three classes should be generalized.
|
||
|
|
<H2> AUTHOR </H2>
|
||
|
|
Andreas Stolcke <stolcke@icsi.berkeley.edu>.
|
||
|
|
<BR>
|
||
|
|
Copyright (c) 2002-2008 SRI International
|
||
|
|
</BODY>
|
||
|
|
</HTML>
|