📄 segment-nbest.html
字号:
<! $Id: segment-nbest.1,v 1.8 2004/12/03 17:59:01 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><B> segment-nbest </B>[<B>-help</B>]<B></B>option...nbest-file-list...<H2> DESCRIPTION </H2><B> segment-nbest </B>processes a series of consecutive N-best lists from a speechrecognizerand 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.html">ngram-format(5)</A>modeling sentence segmentation using the boundary tags <s> and </s>.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 <s> 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 indicatestdin/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><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 modelfile is read, so the same file can be used at various orders.<DT><B>-debug</B><I> level</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><DD>Read the N-gram model from<I>file</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><DD>Read a second, standard N-gram model for interpolation purposes.<DT><B>-lambda</B><I> weight</I><B></B><DD>Set the weight of the main model when interpolating with<B>-mix-lm</B>.<B></B>Default value is 0.5.<DT><B>-bayes</B><I> length</I><B></B><DD>Interpolate the second and the main model using posterior probabilitiesfor local N-gram-contexts of length<I>length</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><DD>Set the exponential scale factor on the context likelihood in conjunctionwith the<B> -bayes </B>function.Default value is 1.0.<DT><B>-nbest-files</B><I> list</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 formatsdescribed in <A HREF="nbest-format.html">nbest-format(5)</A>.The N-best files should correspond to consecutive speech waveformsin the order listed.<DT><B> -fb-rescore </B><DD>Perform Forward-backward rescoring.This generates new N-best listsas output whose LM scores reflect the posterior probability of eachhypothesis.The default is to perform Viterbi rescoring and output only thebest combined hypothesis.<DT><B>-write-nbest-dir</B><I> dir</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><DD>Limits the number of hypotheses read from each N-best list to the first<I>n</I>.<I></I><DT><B>-max-rescore</B><I> m</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 tothe top<I>m</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><DD>Specifies the language model weight to be use in combiningacoustic and language model scores to select the best hypotheses.<DT><B>-rescore-wtw</B><I> weight</I><B></B><DD>Specifies the word transition weight to be used in selecting thebest hypotheses.<DT><B>-noise</B><I> noise-tag</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><DD>Read several noise tags from<I>file</I>,<I></I>instead of, or in addition to, the single noise tag specified by<B>-noise</B>.<B></B><DT><B>-decipher-lm</B><I> model-file</I><B></B><DD>Designates the N-gram backoff model (typically a bigram) that was used by theDecipher(TM) recognizer in computing composite scores.Used to compute acoustic scores from the composite scores if theN-best lists are in "NBestList1.0" format.<DT><B>-decipher-lmw</B><I> weight</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><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><DD>Use<I> string </I>to mark segment boundaries in the output.Default is the start-of-sentence symbol defined in the language model (<s>).<DT><B>-bias</B><I> b</I><B></B><DD>Make a segment boundary a priori more likely by a factor of<I>b</I>.<I></I>If<I> b </I>is 0, the dynamic program algorithm is restricted to never considerhidden 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><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><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 acousticwaveform boundaries with a special tag.</DD></DL><P><B> segment-nbest </B>will also process any command line arguments following the optionsas 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<BR> <nbestfile <I>nbest-file-list</I>><BR><H2> SEE ALSO </H2><A HREF="ngram-count.html">ngram-count(1)</A>, <A HREF="segment.html">segment(1)</A>, <A HREF="ngram-format.html">ngram-format(5)</A>, <A HREF="nbest-format.html">nbest-format(5)</A>.<BR>A. Stolcke, ``Modeling Linguistic Segment and Turn Boundaries for N-bestRescoring 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 precedingN-best list.<H2> AUTHOR </H2>Andreas Stolcke <stolcke@speech.sri.com>.<BR>Copyright 1997-2004 SRI International</BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -