| |
| <HTML><HEAD> |
| <CENTER><TITLE>SC_STATS Command Line Options</TITLE> |
| </HEAD> |
| <BODY></CENTER><p><hr> |
|
|
| <H1> |
| <A NAME="options_name_0"> |
| <A HREF="sc_stats.htm#sc_stats_name_0">Sc_stats</A> Commandline Options</A> |
| </H1> |
| <p> |
| The commandline options for sc_stats can be broken into four categories: |
| <ol type=1> |
| <li><a href="st_opt.htm#input_options_0"> Input File Options: </a> |
| <ul> |
| <a href="st_opt.htm#option_p_name_0">-p</a>, |
| </ul> |
|
|
| <li><a href="st_opt.htm#output_options_0"> Output Options: </a> |
| <ul> |
| <a href="st_opt.htm#option_e_name_0">-e</a>, |
| <a href="st_opt.htm#option_n_name_0">-n</a>, |
| <a href="st_opt.htm#option_O_name_0">-O</a>, |
| </ul> |
| <li><a href="st_opt.htm#report_options_0"> Report Generation Options: </a> |
| <ul> |
| <a href="st_opt.htm#option_r_name_0">-r</a> |
| </ul> |
| <li><a href="st_opt.htm#tests_options_0"> Statistical Test Options: </a> |
| <ul> |
| <a href="st_opt.htm#option_t_name_0">-t</a> |
| <a href="st_opt.htm#option_v_name_0">-v</a> |
| <a href="st_opt.htm#option_u_name_0">-u</a> |
| <a href="st_opt.htm#option_g_name_0">-g</a> |
| </ul> |
| </ol> |
|
|
| <p> |
| <a name="input_options_0"><strong> Input File Options: </strong></a> |
| <UL> |
|
|
| These options control/define the input to sc_stats. Input must |
| come from stdin and the -p option must be used. (Forcing the user to |
| use the -p option enables future expandability while maintaining backward |
| compatability.) |
|
|
| <br> |
| <br> |
| <a name="option_p_name_0">-p</a> |
| <ul> |
| Alignments are read from 'stdin' as input to sc_stats. |
| The format of the input must be in the "sgml" output |
| format, created either by '-o sgml' or by piped input |
| from another sctk utility. |
| </ul> |
|
|
| </ul> |
|
|
| <a name="output_options_0"><strong> Output Options: </strong></a> |
| <ul> |
| <a name="option_e_name_0">-e desc</a> |
| <ul> |
| Description of the ensemble of hyp files. |
| </ul> |
| <a name="option_O_name_0">-O output_dir </a> |
| <ul> |
| Writes all output files into output_dir. Defaults to the |
| hypfile's directory |
| </ul> |
| <a name="option_n_name_0">-n name </a> |
| <ul> |
| Writes all multiple hypothesis file reports to files beginning |
| with 'name'. Using '-' writes to stdout. Default: 'Ensemble' |
| </ul> |
| </ul> |
|
|
| <a name="report_options_0"><strong> Report Generation Options: </strong></a> |
| <ul> |
| <a name="option_g_name_0">-g</a> [ range | grange | grange2 ] </a> |
| <ul> |
| Generate per speaker range graphs, based on the formula defined |
| by '-f'. The reports are written to files whose root name |
| begins with the values defined by '-n'. There are two graphs |
| produced, one showing speaker performance variability across |
| systems and the |
| second showing system performance variablity for across speakers. |
| <p>- The '<STRONG>range</STRONG>' graphs are an ASCII |
| representation of the |
| of the variablity in error rates for a given speaker. The |
| graph is sorted be the mean of statistic computed for each speaker. |
| <A HREF="st_out.htm#sc_out_range_0">EXAMPLE</A> |
| |
| <p> - The '<STRONG>grange</STRONG>' graph is a gnuplot version of the same data |
| ploted in 'range. There are two sets of files created. |
| The first set, which is called '*.grange.spk.plt' and |
| '*.grange.spk.dat', contains the gnuplot command files and |
| data files respectively for the speaker performance variability |
| across systems graph. |
| The second set, which is called '*.grange.sys.plt' and |
| '*.grange.sys.dat', contains the gnuplot command files and |
| data files respectively for the system |
| performance variability across speakers graph. |
|
|
| <A HREF="st_out.htm#sc_out_grange_0">EXAMPLE</A> |
|
|
| <p> - The '<STRONG>grange2</STRONG>' graph is similar to the 'grange' |
| graph except that each systems speaker word error scores are |
| identified by a unique symbol. |
| <A HREF="st_out.htm#sc_out_grange2_0">EXAMPLE</A> |
| </ul> |
| <BR> |
| <a name="option_r_name_0">-r</a> [ sum | rsum | lur | es | res | none ] </a> |
| <ul> |
| <dl> |
| <dt> |
| prn - |
| <dd> |
| <a href="st_out.htm#st_out_prn_0">Example</a> |
| <dt> |
| sum - |
| <dd> |
| <a href="st_out.htm#st_out_sum_0">Example</a> |
| <dt> |
| rsum - |
| <dd> |
| <a href="st_out.htm#st_out_rsum_0">Example</a> |
| <dt> |
| lur - |
| <dd> |
| <a href="st_out.htm#st_out_lur_0">Example</a> |
| <dt> |
| es - |
| <dd> |
| <a href="st_out.htm#st_out_es_0">Example</a> |
| <dt> |
| res - |
| <dd> |
| <a href="st_out.htm#st_out_res_0">Example</a> |
| <dt> |
| none - |
| <dd> |
| Produce no output reports, Default. |
| </dl> |
| </ul> |
| </ul> |
|
|
| <a name="tests_options_0"><strong> Statistical Test Options: </strong></a> |
| <ul> |
| <a name="option_t_name_0">-t</a> [ mcn | mapsswe | sign | wilc | anovar | std4 ] |
| <ul> |
| <dl> |
| <dt> |
| mcn - |
| <dd> |
| Perform the McNemar Test. |
| <dt> |
| mapsswe - |
| <dd> |
| Perform the Matched Pairs Sentence Segment Word Error Test |
| <dt> |
| sign - |
| <dd> |
| Perform the Sign Test |
| <dt> |
| wilc - |
| <dd> |
| Perform the Wilcoxon Signed Rank Test |
| <dt> |
| anovar - |
| <dd> |
| Perform the Analysis of Variance by Rank Test |
| <dt> |
| std - |
| <dd> |
| This is a shorthand notation to do the 'standard' four tests: |
| mcn, mapsswe, wilc and sign. |
| </dl> |
| </ul> |
| <BR> |
| <a name="option_v_name_0">-v</a> |
| <UL> |
| For each test performed on a pair of systems files, output a |
| detailed analysis. |
| </UL> |
| <BR> |
| <a name="option_u_name_0">-u</a> |
| <UL> |
| Rather than creating a comparison matrix for each test, unify |
| statistical test results into a single comparison matrix |
| </UL> |
| <BR> |
| <a name="option_u_name_0">-f</a> [ E | R | W ] |
| <UL> |
| Use the identified formula for statistical tests: sign, |
| wilcoxon and anovar tests. The formulas are: |
| <OL> |
| <LI> E -> Percentage Word Error |
| <LI> R -> Percentage Words Correctly Recognized |
| <LI> E -> Percentage Word Accuracy |
| </OL> |
| By default 'E' |
| </UL> |
|
|
| </ul> |
|
|
| </body> |
| </html> |
|
|
