Files
b2txt25/language_model/srilm-1.7.3/man/html/segment-nbest.1.html
2025-07-02 12:18:09 -07:00

212 lines
7.7 KiB
HTML

<! $Id: segment-nbest.1,v 1.10 2019/09/09 22:35:37 stolcke Exp $>
<HTML>
<HEADER>
<TITLE>segment-nbest</TITLE>
<BODY>
<H1>segment-nbest</H1>
<H2> NAME </H2>
segment-nbest - rescore and segment N-best lists using hidden segment N-gram model
<H2> SYNOPSIS </H2>
<PRE>
\fsegment-nbest\fP [ <B>-help</B> ] <I>option</I> ... <I>nbest-file-list</I> ...
</PRE>
<H2> DESCRIPTION </H2>
<B> segment-nbest </B>
processes a series of consecutive N-best lists from a speech
recognizer
and applies a hidden segment N-gram language model to them.
The language model is a standard backoff N-gram model in ARPA
<A HREF="ngram-format.5.html">ngram-format(5)</A>
modeling sentence segmentation using the boundary tags &lt;s&gt; and &lt;/s&gt;.
The program reads in all N-best lists and outputs the
hypotheses that have the highest aggregate (combined acoustic
and language model) score.
Hypothesized sentence boundaries are marked by &lt;s&gt; tags.
<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>-order</B><I> n</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Set the maximal N-gram order to be used, by default 3.
NOTE: The order of the model is not set automatically when a model
file is read, so the same file can be used at various orders.
<DT><B>-debug</B><I> level</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Set the debugging output level (0 means no debugging output).
Debugging messages are sent to stderr.
<DT><B>-lm</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Read the N-gram model from
<I>file</I>.<I></I><I></I><I></I>
<DT><B> -tolower </B>
<DD>
Map all vocabulary to lowercase.
Useful if case conventions for N-best lists and language model differ.
<DT><B>-mix-lm</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Read a second, standard N-gram model for interpolation purposes.
<DT><B>-lambda</B><I> weight</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Set the weight of the main model when interpolating with
<B>-mix-lm</B>.<B></B><B></B><B></B>
Default value is 0.5.
<DT><B>-bayes</B><I> length</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Interpolate the second and the main model using posterior probabilities
for local N-gram-contexts of length
<I>length</I>.<I></I><I></I><I></I>
The
<B> -lambda </B>
value is used as a prior mixture weight in this case.
<DT><B>-bayes-scale</B><I> scale</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Set the exponential scale factor on the context likelihood in conjunction
with the
<B> -bayes </B>
function.
Default value is 1.0.
<DT><B>-nbest-files</B><I> list</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Specifies a list of N-best files.
The file
<I> list </I>
should contain a list of filenames, one per line,
each corresponding to an N-best file in one of the formats
described in
<A HREF="nbest-format.5.html">nbest-format(5)</A>.
The N-best files should correspond to consecutive speech waveforms
in the order listed.
<DT><B> -fb-rescore </B>
<DD>
Perform Forward-backward rescoring.
This generates new N-best lists
as output whose LM scores reflect the posterior probability of each
hypothesis.
The default is to perform Viterbi rescoring and output only the
best combined hypothesis.
<DT><B>-write-nbest-dir</B><I> dir</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Write rescored N-best lists to directory
<I> dir </I>
instead of to stdout.
The filenames from the input are preserved.
<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 each N-best list to the first
<I>n</I>.<I></I><I></I><I></I>
<DT><B>-max-rescore</B><I> m</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Only choose among the top
<I> m </I>
hypotheses of each list (after reordering hypotheses, see below).
This is an effective way to limit the quadratic computation
of the Viterbi or forward/backward dynamic programming.
<DT><B> -no-reorder </B>
<DD>
Do not reorder the hypotheses before limiting the computation to
the top
<I>m</I>.<I></I><I></I><I></I>
By default the hypotheses will first be sorted according to the
acoustic and language model scores recorded in the N-best lists.
<DT><B>-rescore-lmw</B><I> weight</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Specifies the language model weight to be use in combining
acoustic and language model scores to select the best hypotheses.
<DT><B>-rescore-wtw</B><I> weight</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Specifies the word transition weight to be used in selecting the
best hypotheses.
<DT><B>-noise</B><I> noise-tag</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Designate
<I> noise-tag </I>
as a vocabulary item that is to be ignored by the LM.
(This is typically used to identify a noise marker.)
<DT><B>-noise-vocab</B><I> file</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Read several noise tags from
<I>file</I>,<I></I><I></I><I></I>
instead of, or in addition to, the single noise tag specified by
<B>-noise</B>.<B></B><B></B><B></B>
<DT><B>-decipher-lm</B><I> model-file</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Designates the N-gram backoff model (typically a bigram) that was used by the
Decipher(TM) recognizer in computing composite scores.
Used to compute acoustic scores from the composite scores if the
N-best lists are in "NBestList1.0" format.
<DT><B>-decipher-lmw</B><I> weight</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Specifies the language model weight used by the recognizer.
Used to compute acoustic scores from the composite scores.
<DT><B>-decipher-wtw</B><I> weight</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Specifies the word transition weight used by the recognizer.
Used to compute acoustic scores from the composite scores.
<DT><B>-stag</B><I> string</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Use
<I> string </I>
to mark segment boundaries in the output.
Default is the start-of-sentence symbol defined in the language model (&lt;s&gt;).
<DT><B>-bias</B><I> b</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Make a segment boundary a priori more likely by a factor of
<I>b</I>.<I></I><I></I><I></I>
If
<I> b </I>
is 0, the dynamic program algorithm is restricted to never consider
hidden sentence boundaries; this is useful when
<B> segment-nbest </B>
is used merely for its ability to apply the LM across N-best boundaries.
<DT><B>-start-tag</B><I> string</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Insert a tag
<I> string </I>
at the front of every N-best hypothesis read in.
<DT><B>-end-tag</B><I> string</I><B></B><I></I><B></B><I></I><B></B>
<DD>
Insert a tag
<I> string </I>
at the end of every N-best hypothesis read in.
This and the previous option are useful if the LM marks acoustic
waveform boundaries with a special tag.
</DD>
</DL>
<P>
<B> segment-nbest </B>
will also process any command line arguments following the options
as lists of N-best lists, as with the
<B> -nbest-files </B>
option.
Each
<I> nbest-file-list </I>
will be processed in turn,
with individual output delimited by a line of the form
<PRE>
&lt;nbestfile <I>nbest-file-list</I>&gt;
</PRE>
<H2> SEE ALSO </H2>
<A HREF="ngram-count.1.html">ngram-count(1)</A>, <A HREF="segment.1.html">segment(1)</A>, <A HREF="ngram-format.5.html">ngram-format(5)</A>, <A HREF="nbest-format.5.html">nbest-format(5)</A>.
<BR>
A. Stolcke, ``Modeling Linguistic Segment and Turn Boundaries for N-best
Rescoring of Spontaneous Speech,'' <I>Proc. Eurospeech</I>, 2779-2782, 1997.
<H2> BUGS </H2>
N-gram models of arbitrary order can be used, but the context at the
beginning of a hypothesis never extends beyond the words from the preceding
N-best list.
<H2> AUTHOR </H2>
Andreas Stolcke &lt;stolcke@icsi.berkeley.edu&gt;
<BR>
Copyright (c) 1997-2004 SRI International
</BODY>
</HTML>