📄 nbest-pron-score.html
字号:
<! $Id: nbest-pron-score.1,v 1.5 2004/12/03 17:59:01 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>]<B></B><I> option </I>...<H2> DESCRIPTION </H2><B> nbest-pron-score </B>reads N-best lists and computes log probability scores for the pronunciationsand pauses contained in them.Pronunciation scoring requires that the N-best listscontain phone backtraces in "NBestList2.0"<A HREF="nbest-format.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 lengthon the left and right neighboring words, in that order (so that bigrambackoff 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 indicatestdin/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><DD>Controls the amount of output (the higher the<I>level</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 splitand only the component closest to the pause is conditioned on.<DT><B>-nbest</B><I> file</I><B></B><DD>Score the N-best hypothese in <I>file</I>.<I></I><DT><B>-rescore</B><I> file</I><B></B><DD>Same as <B>-nbest</B>.<B></B><DT><B>-nbest-files</B><I> file</I><B></B><DD>Process all N-best list filenames listed in <I>file</I>.<I></I><DT><B>-max-nbest</B><I> n</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><DD>Enable pronunciation scoring, using the pronunciation dictionary <I>file</I>.<I></I>Each line contains a pronunciation in the format<BR> <I>word</I> [<I>p</I>] <I>phone</I> ...<BR>The optional value <I> p </I>is the pronunciation probability.If the second field in a line is not a number the pronunciation is assumedto 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><DD>Enable pause scoring, using the pause LM in<I>file</I>.<I></I><DT><B>-no-pause</B><I> tag</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><DD>The word used to represent a short pause in the pause LM.<DT><B>-long-pause</B><I> tag</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><DD>The minimum duration, in seconds, for a non-speech region to be considereda (short) pause.<DT><B>-long-pause-dur</B><I> T</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><DD>Write pronunciation scores to<I>dir</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><DD>Write pause scores to<I>dir</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><DD>Add pause LM scores to the pronunciation scores after multiplying themby <I>W</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></DD></DL><H2> SEE ALSO </H2><A HREF="nbest-format.html">nbest-format(5)</A>, <A HREF="nbest-scripts.html">nbest-scripts(1)</A>, <A HREF="nbest-optimize.html">nbest-optimize(1)</A>, <A HREF="ngram.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@speech.sri.com>.<BR>Copyright 2002-2004 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 + -