| |
| <HTML><HEAD> |
| <CENTER><TITLE>SCLITE Command Line Options</TITLE> |
| </HEAD> |
| <BODY></CENTER><p><hr> |
|
|
| <H1> |
| <A NAME="options_name_0"> |
| <A HREF="sclite.htm#sclite_name_0">Sclite</A> Commandline Options</A> |
| </H1> |
| <p> |
| The commandline options for <A HREF="sclite.htm#sclite_name_0">sclite</A> |
| can be broken into four categories: |
| <ol type=1> |
| <li><a href="options.htm#input_options_0"> Input File Options: </a> |
| <ul> |
| <a href="options.htm#option_e_name_0">-e</a>, |
| <a href="options.htm#option_h_name_0">-h</a>, |
| <a href="options.htm#option_i_name_0">-i</a>, |
| <a href="options.htm#option_P_name_0">-P</a>, |
| <a href="options.htm#option_r_name_0">-r</a>, |
| <a href="options.htm#option_R_name_0">-R</a> |
| </ul> |
|
|
| <li><a href="options.htm#alignment_options_0"> Alignment Options: </a> |
| <ul> |
| <a href="options.htm#option_c_name_0">-c</a>, |
| <a href="options.htm#option_d_name_0">-d</a>, |
| <a href="options.htm#option_D_name_0">-D</a>, |
| <a href="options.htm#option_F_name_0">-F</a>, |
| <a href="options.htm#option_L_name_0">-L</a> |
| <a href="options.htm#option_m_name_0">-m</a>, |
| <a href="options.htm#option_s_name_0">-s</a>, |
| <a href="options.htm#option_S_algo1_name_0">-S</a>, |
| <a href="options.htm#option_T_name_0">-T</a> |
| <a href="options.htm#option_w_name_0">-w</a> |
| </ul> |
| <li><a href="options.htm#output_options_0"> Output Options: </a> |
| <ul> |
| <a href="options.htm#option_f_name_0">-f</a>, |
| <a href="options.htm#option_l_name_0">-l</a>, |
| <a href="options.htm#option_O_name_0">-O</a>, |
| <a href="options.htm#option_p_name_0">-p</a> |
| </ul> |
| <li><a href="options.htm#report_options_0"> Scoring Report Options: </a> |
| <ul> |
| <a href="options.htm#option_C_name_0">-C</a>, |
| <a href="options.htm#option_n_name_0">-n</a>, |
| <a href="options.htm#option_o_name_0">-o</a> |
| </ul> |
| </ol> |
|
|
|
|
|
|
| <p> |
| <a name="input_options_0"><strong> Input File Options: </strong></a> |
| <UL> |
|
|
| These options control/define the input to |
| <A HREF="sclite.htm#sclite_name_0">sclite</A>. Input can come from either |
| reference and hypothesis files, or piped input from previously aligned REF and |
| HYP files. |
| <br> |
| <br> |
| <a name="option_e_name_0">-e gb|euc</a> |
| <ul> |
| Define the character encoding used for the text portion |
| input ref and hyp files. The flag "gb" stands for GB |
| encoded Chinese and "euc" stands for EUC encoded |
| Japanese. Both encodings are 2-byte per character |
| encodings. The default, is extended ASCII. |
| </ul> <br> |
| <a name="option_h_name_0">-h</a> |
| hypfile [ |
| <a href="infmts.htm#trn_fmt_name_0">trn</a> | |
| <a href="infmts.htm#txt_fmt_name_0">txt</a> | |
| <a href="infmts.htm#ctm_fmt_name_0">ctm</a> ] title |
| <ul> |
|
|
| The '-h' option is a required argument which specifies |
| the input hypothesis file. The optional format field, |
| "[ <a href="infmts.htm#trn_fmt_name_0">trn</a> | |
| <a href="infmts.htm#txt_fmt_name_0">txt</a> | |
| <a href="infmts.htm#ctm_fmt_name_0">ctm</a>] " |
| specifies the input file format from the set |
| of input formats described above. The default input |
| format is "<a href="infmts.htm#trn_fmt_name_0">trn</a>". When reports are generated, the "hypfile" name will be used to identify the origins of the |
| results. If the "title" option is used, that string |
| will be used instead. |
|
|
| <p> The -h option may be used more than once to align multiple files. |
| </ul> <br> |
| <a name="option_i_name_0">-i [ wsj | atis | rm | swb | spu_id ] </a> |
| <ul> |
| The '-i' option defines how to interpret the utterance |
| id's used in the transcription input file format "<a href="infmts.htm#trn_fmt_name_0">trn</a>" |
| described above. This argument identifies the corpus of |
| the utterance id: |
| <br> |
| <br> |
| <dl> |
| <dt> |
| wsj - |
| <dd> |
| for Wall Street Journal and CSRNAB |
| <dt> |
| atis - |
| <dd> |
| for ATIS3 |
| <dt> |
| rm | swb | spu_id - |
| <dd> |
| are synonyms which refer to generic utterance id |
| formats whereby the utterance id is made up of a |
| speaker code, followed by a hyphen or underscore, |
| followed by an utterance number. |
| </dl> |
| <p> |
| This option is only required for aligning transcript |
| inputs (<a href="infmts.htm#trn_fmt_name_0">trn</a>). |
|
|
| <comment> TBD </comment> |
| </ul> <br> |
| <a name="option_P_name_0">-P</a> |
| <ul> |
| Alignments are read from 'stdin' as input to sclite. |
| The format of the input must be in the "sgml" output |
| format, created either by '-o sgml' or by piped input |
| from another sclite utility. No re-alignments are performed on the read in alignments, only scoring reports |
| can be generated. |
| </ul> <br> |
| <a name="option_r_name_0">-r</a> reffile [ |
| <a href="infmts.htm#trn_fmt_name_0">trn</a> | |
| <a href="infmts.htm#stm_fmt_name_0">stm</a> | |
| <a href="infmts.htm#ctm_fmt_name_0">ctm</a> ] |
| <ul> |
| The '-r' option, a required argument, specifies the |
| input reference file which the hypothesis file(s) are |
| compared to. The optional format field |
| "[ <a href="infmts.htm#trn_fmt_name_0">trn</a> | |
| <a href="infmts.htm#stm_fmt_name_0">stm</a> | |
| <a href="infmts.htm#ctm_fmt_name_0">ctm</a> ] " |
| field specifies the |
| input file format from the set of input formats |
| described above. The default input format is "<a href="infmts.htm#trn_fmt_name_0">trn</a>". |
| </ul> <br> |
| <a name="option_R_name_0">-R</a> |
| <ul> |
| Interpret the text symbols as a right-to-left language such as |
| Arabic. The default is to interpret text in a left-to-right fashion |
| as in English. |
| </ul> <br> |
| </ul> |
| <a name="alignment_options_0"><strong> Alignment Options: </strong></a> |
| <ul> |
| <a name="option_c_name_0">-c [ NOASCII DH ]</a> |
| <ul> |
| Chop up the words into separate characters before doing |
| the alignment. It is generally not the practice of the |
| ARPA community to score at the character level. The |
| intent of this option is to be able to score Mandarin |
| Chinese at the character level. The option "NOASCII" |
| does not separate characters if they are ASCII. The |
| option "DH" deletes hyphens from the ref and hyp |
| strings before alignment. This option only works using |
| the DP alignment algorithm. (-c & -d are exclusive) |
| </ul> <br> |
| <a name="option_d_name_0">-d</a> |
| <ul> |
| Use <a href="sclite.htm#gnu_diff_alignment_0">GNU diff</a> |
| for alignments rather than the default |
| dynamic programming. (-c & -d are exclusive) |
|
|
| </ul> <br> |
| <a name="option_D_name_0">-D</a> |
| <ul> |
| Perform <a href="sclite.htm#optional-word-scoring">Optional Word Scoring</a>. Word errors involving words marked as 'optional' are forgiven by counting them as correct. (-D & -d are exclusive) |
|
|
| </ul> <br> |
| <a name="option_F_name_0">-F</a> |
| <ul> |
| Perform the alignment using a cost function which |
| counts fragments, words ending or beginning with a |
| hyphen, as correct if the spelling up to the hyphen |
| matches the spelling of the hypothesized word. |
| Options -F and -d are exclusive. |
| </ul> <br> |
| <a name="option_L_name_0">-L LM</a> |
| <ul> |
|
|
| Define the <A HREF="../src/slm_v2/doc/toolkit_documentation.html"> |
| CMU-Cambridge Statistical Language Modeling Toolkit v2</A> language |
| mode file to be 'LM'. The LM file must be created using the |
| <A HREF="../src/slm_v2/doc/toolkit_documentation.html#idngram2lm">idngram2lm</A> program. |
| (See the toolkit documentation details of how |
| to make the language model.) Currently, SCTK supports 1, 2 and 3-grams. |
|
|
| <P> The language model is used to compute an individual weight for each |
| word in the reference and hypothesis strings. The weight is defined |
| to be <i>Log<sub>2</sub>(P(word|context))</i>. Each pair of aligned |
| strings is considered to be independent, so therefore, there is |
| no context for initial words in each pair. |
|
|
| <P> |
| The word-weights are used in two ways, first as a method to define word-to-word distances |
| for <A href="sclite.htm#word-weight-mediated"> word-weight-mediated alignment </A> |
| and second to perform <A HREF="sclite.htm#weighted-word-scoring"> |
| weighted word scoring </A>. |
|
|
| <P> Out-of-Vocabulary words get the default weight of 20.0, and optionally |
| deletable words get a default weight of 0.0. |
|
|
| </ul> <br> |
| <a name="option_m_name_0">-m [ ref | hyp ]</a> |
| <ul> |
| When scoring a hypothesis ctm file against a reference |
| stm file, the time spans of the two may not match, |
| (i.e. the start time of the first word/segment may not |
| match or the end time of the last word/segment may not |
| match). |
| <p> |
| When this option is used, the alignment phase of scoring |
| ignores any segment or word (depending on the |
| option(s) used) which is not in the time span of the |
| opposite file. The time span of a file is defined to |
| be start time of the first time mark, to the end time |
| of the last time mark. |
| <p> |
| The "ref" option reduces the reference segments to |
| those which are within the hypothesis file time span. |
| <p> |
| The "hyp" option reduces the hypothesis words to those |
| which are within the reference file tiem span. |
| <p> |
| Both "ref" and "hyp" may be used simultaneously. |
| <p> |
| The argument -m by itself defaults to '-m ref'. |
| Exclusive with -d. |
|
|
| </ul> <br> |
| <a name="option_s_name_0">-s</a> |
| <ul> |
| Do Case-sensitive alignments. Otherwise all input is mapped to |
| a single case before scoring. Of course, GB and UEX encode text |
| data is never case-converted. |
| </ul> <br> |
| <a name="option_S_algo1_name_0">-S algo1 lexicon [ ASCIITOO ] </a> |
| <ul> |
| The '-S' option performs an inferred word segmentation |
| alignment algorithm. This option |
| is intended to be used for the LVCSR evaluation of Mandarin |
| Chinese. A problem with scoring Mandarin at the |
| word level is the lack of clearly defined words in Mandari |
| text. This option implements an algorithm which, |
| given a word segmentation for the reference string and |
| a "lexicon" of legal words, computes a minimal error |
| rate word alignment. The algorithm is as follows: |
| <br> <br> |
| <ol type=1> |
| <li> Convert the previously word-segmented reference |
| string into a word network. |
|
|
| <li> Covert the hypothesis text to a string of characters, |
| each character representing a word. The data |
| represented is then convert to a network. |
| <pre> |
| ex. * --- A --- * --- T --- * --- 0 --- * |
| </pre> |
| <li> Consider all possible sequences of letters through |
| the network. If a sequence creates a word which is |
| represented in the lexicon, add an arc to the network |
| representing the word. The maximum characters per word |
| is limited to the maximum word length in the lexicon. |
| <pre> |
| ,-------- TO -------. |
| / \ |
| ex. * --- A --- * --- T --- * --- 0 --- * |
| \ / |
| `------- AT --------' |
| </pre> |
| <li> DP Align the reference and hypothesis networks, and |
| extract a minimal cost path. |
| </ol> |
| <p> |
| The supplied "lexicon" must be a sorted list of word |
| records, each separated by a newline. Only the first |
| column, separated by whitespace, is read in and used |
| for the lexicon. By default, the algorithm only |
| separates hypothesis characters that are GB or EUC |
| encoded. If the option "ASCIITOO" is used, ASCII |
| hypothesis words are also converted to characters in |
| step 2. |
| <p>Exclusive with -d. |
| </ul><br> |
| <a name="option_S_algo2_name_0">-S algo2 lexicon [ ASCIITOO ] </a> |
| <ul> |
| Perform a similar algorithm as described in '-S alog1' except |
| the roles of the reference and hypothesis transcripts are reversed. |
| In this algorithm, the segmentation of the hypothesis text is held |
| constant, while the reference transcript undergoes the process of |
| of coversion to characters and arcs added to the network for words |
| found in the lexicon. Both "lexicon" and "ASCIITOO" have the same |
| usage as in algo1. |
| <p>Exclusive with -d. |
| </ul> <br> |
| <a name="option_T_name_0">-T</a> |
| <ul> |
| The '-T' option performs time-mediated string alignments rather than the traditional word alignments. |
| Currently, only alignments involving two "ctm" files |
| can be aligned in this manner. The <A HREF="sclite.htm#time-mediated"> main SCLITE</A> |
| page describes time-mediated alignments. |
| <p> |
| Options -F and -d are exlcusive. |
| </ul> <br> |
| <a name="option_w_name_0">-w wwl_file</a> |
| <ul> |
|
|
| Define the word-weight list (WWL) file to be 'wwl_file'. The WWL file |
| defines an arbitrary weight for each word in the lexicon. The weights are |
| used in two ways, first as a method to define word-to-word distances |
| for <A href="sclite.htm#weighted-word-scoring"> word-weight-mediated alignment </A> |
| and second to perform <A HREF="sclite.htm#word-weight-scoring"> |
| weighted word scoring </A>. |
|
|
| <P> If the supplied WWL filename is "unity", then no file of weights is read in. |
| Instead, this is a shorthand notation to use a weight of 1.0 for all words. |
|
|
| <P> Optionally deletable words get a default weight of 0.0, (even if "unity" |
| is supplied as the WWL filename). |
|
|
| <P> The format of the WWL file is as follows. <BR><BR> |
| <UL> |
|
|
| Comment lines begin with |
| double semi-colons. The are two forms of "special" comment lines. The |
| first defines heading labels each column in the table. The format for this |
| line is: <br> <br> |
| <UL> ;; 'Headings' '<COL1>' '<COL2>' '<COL3>' .... </UL> <BR> |
| The label for column 1 should be "Word Spelling" since this column is the |
| word's text. The labels for columns 2 though 10 are defined by the user. |
| <P> |
| The second "special" comment line defines the default weight applied to |
| out-of-vocabulary words if any exist. The format for this line is: <br> <br> |
| <UL> ;; Default missing weight '<number>' </UL> <br> |
| 'number' must be a floating point number. |
| <P> |
| The remainder of the file consists of word records, each word record separated by |
| a newline. The format of each record is: <br> <br> |
| <UL> <WORD_TEXT> <WEIGHT_1> <WEIGHT_2> . . . </UL> <br> |
| There should be no whitespace at the beginning if the line, and the word |
| texts can not include whitespace. The remainder of the line are whitespace |
| separated floating point weights, up to a maximum of 10 weights can |
| be assigned per word. |
| <P> |
| <B>NOTE: The current version of SCTK only utilizes the first weight.</B> |
| </UL> |
| </ul> <br> |
| </ul> |
|
|
| <a name="output_options_0"><strong> Output Options: </strong></a> |
| <ul> |
| <a name="option_f_name_0">-f level</a> |
| <ul> |
| As a well behaved program, reassure the user that the |
| program is continuing to perform it's task by providing |
| the user with some feedback. The feedback levels, |
| defined by this option are: 0) no feedback, 1) processing feedback (i.e. status of text loading and alignments); 2) processing feedback plus printing out |
| aligned strings. The feedback level defaults to 0 if |
| no output options are specified using the '-o' option, |
| otherwise it defaults to 1. |
| </ul> |
| <br> |
| <a name="option_l_name_0">-l width</a> |
| <ul> |
| When printing the text alignments for the output option |
| "pralign" wrap the lines at "width" characters. |
| Default is 1000 characters. |
| </ul> |
| <br> |
| <a name="option_O_name_0">-O output_dir</a> |
| <ul> |
| Instead of writing the output files to the directory |
| containing the <hypfile>, write them into the directory |
| "output_dir". If the output directory does not exist, |
| all reports will be written to stdout. |
| </ul> |
| <br> |
| <a name="option_p_name_0">-p</a> |
| <ul> |
| Write to standard out the resulting alignments so they |
| can be piped to another sclite utility. The format of |
| the output is the same as '-o sgml'. The options sets |
| the feedback level, with '-f' to 0. |
| </ul> |
| </ul> |
|
|
| <a name="report_options_0"><strong> Scoring Report Options: </strong></a> |
|
|
| <ul> |
| <a name="option_C_name_0">-C [ det | bhist | hist | none ] </a> |
| <ul> |
| Defines the output formats for analysis of confidence scores. |
| Currently, the only way to assign confidence estimates to |
| each hyp word is through the <a href="infmts.htm#ctm_fmt_name_0">ctm</a> hypothesis file. |
| Default: 'none' |
| <a href="outputs.htm#output_graphs_name_0"> Examples. </a> |
|
|
| </ul> |
| <br> |
| <a name="option_n_name_0">-n name</a> |
| <ul> |
| Writes all outputs using 'name' as a root filename instead of |
| 'hypfile'. For multiple hypothesis files, the root filename |
| is 'name'.'hypfile' |
| </ul> |
| <br> |
| <a name="option_o_name_0">-o</a> [ sum | rsum | wws | pralign | all | sgml | stdout | lur | snt | spk | dtl | prf | none ] |
| <ul> |
| Defines the output scoring reports generated by the |
| sclite. The possible reports are: |
| <br> |
| <br> |
| <dl> |
| <dt> |
| sum - |
| <dd> |
| Produce a summary of speaker performance in terms |
| of Percents: Correct, Substitutions, Deletions, |
| Insertions, Word Errors and Sentence (or Utterance) errors. System averages and speaker means, |
| medians and standard deviations are computed for |
| each percentage. If the report is not going to |
| stdout, the output is placed in a file called |
| "<hypfile>.sys". The options '-O' and '-n' can |
| change the destination of the output file. |
| <a href="outputs.htm#outputs_sum_name_0">Example</a> |
| <dt> |
| rsum - |
| <dd> |
| Produce a summary similar to 'sum' except output |
| word counts instead of percentages. If the report |
| is not going to stdout, the output is placed in a |
| file called <hypfile>.raw. The options '-O' and |
| '-n' can change the destination of the output |
| file. |
| <a href="outputs.htm#outputs_rsum_name_0">Example</a> |
| <dt> |
| wws - |
| <dd> |
| Produce a summary similar to 'sum' except output |
| <A HREF="sclite.htm#weighted-word-scoring">weighted word error</A> instead of word error. If the report |
| is not going to stdout, the output is placed in a |
| file called <hypfile>.wws. The options '-O' and |
| '-n' can change the destination of the output |
| file. |
| <a href="outputs.htm#outputs_wws_name_0">Example</a> |
| <dt> |
| pralign - <br> |
| pra - |
| <dd> |
| Produce a text copy of all the string alignments. |
| If the report is not going to stdout, the output |
| is placed in a file called <hypfile>.pra. The |
| options '-O' and '-n' can change the destination |
| of the output file. "pralign" and "pra" are synonyms. |
| <a href="outputs.htm#outputs_pralign_name_0">Example</a> |
| <dt> |
| prf - |
| <dd> |
| Produce a text copy of all the string alignments similar |
| to that produced by "pralign" except, include all relevant |
| information concerning the alignments. That is, include |
| in the output things like: word beginning and ending times, |
| reference |
| segment beginning and ending times, and hypothesis word |
| confidence scores. |
| <a href="outputs.htm#outputs_prf_name_0">Example</a> |
| <dt> |
| all - |
| <dd> |
| Produces the three reports: |
| "<a href="outputs.htm#outputs_sum_name_0">sum</a>", |
| "<a href="outputs.htm#outputs_rsum_name_0">rsum</a>", and |
| <a href="outputs.htm#outputs_pralign_name_0">pralign</a>" |
| <dt> |
| stdout - |
| <dd> |
| Write all selected scoring reports to stdout. If |
| the feedback level is not specified using the '-f' |
| option, the feedback level is set to 0. |
| <dt> |
| sgml - |
| <dd> |
| Produce a dump of the text alignments in an sgml |
| notation. The output consists of tags at the system, speaker, and sentence level. Text information is only present at the sentence level and |
| consists a comma separated list of word alignments. The word alignments can be either of the |
| following: C:"word" or I:"word" or D:"word" or |
| S:"word1","word2" for correct, insertion, deletion |
| and substitution respectively. If the report is |
| not going to stdout, the output is placed in a |
| file called <hypfile>.sgml. The options '-O' and |
| '-n' can change the destination of the output |
| file. |
| <a href="outputs.htm#outputs_sgml_name_0">Example</a> |
| <dt> |
| lur - |
| <dd> |
| Produce a Labeled Utterance Report (LUR) based |
| information in the reference STM file. (Note: only |
| reference files in STM format support this |
| option.) The LUR report is a report which tabulates overall error rate statistics and statistics |
| over arbitrary subsets of the reference data, e.g. |
| speaker's sex, audio characteristics. If the |
| report is not going to stdout, the output is |
| placed in a file called <hypfile>.lur. The |
| options '-O' and '-n' can change the destination |
| of the output file. |
| <a href="outputs.htm#outputs_lur_name_0">Example</a> |
| <dt> |
| snt - |
| <dd> |
| Produce a scoring report file for all |
| utterance/segments of a speaker. Within each |
| file, one per speaker, is a by-utterance error |
| analysis which contains: the aligned text, error |
| classification percentages and other statistics. |
| If the report is not going to stdout, the output |
| is placed in a file called |
| <hypfile>.snt.<speaker_id>. The options '-O' and |
| '-n' can change the destination and name of the |
| output file. |
| <a href="outputs.htm#outputs_snt_name_0">Example</a> |
| <dt> |
| spk - |
| <dd> |
| Produce a scoring report file summarizing the |
| errors made on the speaker's utterances. Within |
| each file, one per speaker id, is a summarization |
| of utterance and word errors along with confusion |
| pair, insertion, deletion, substitution and |
| falsely recognized word lists. |
| If the report is not going to stdout, the output |
| is placed in a file called |
| <hypfile>.spk.<speaker_id>. The options '-O' and |
| '-n' can change the destination and name of the |
| output file. |
| <a href="outputs.htm#outputs_spk_name_0">Example</a> |
| <dt> |
| dtl - |
| <dd> |
| Produce a scoring report in the same format as the |
| "spk" report using statistics gathered over the |
| entire test set. If the report is not going to |
| stdout, the output is placed in a file called |
| <hypfile>.dtl. The options -'O' and '-n' can |
| change the destination and name of the output |
| file. |
| <a href="outputs.htm#outputs_dtl_name_0">Example</a> |
| <dt> |
| none - |
| <dd> |
| Produce no output reports. |
| </dl> |
| <p> |
| If this option is not specified, the default options |
| are "sum" and "stdout". If the user wishes to have |
| reports other than "sum" to be written to stdout, then |
| the "stdout" flag must be used in the argument list. |
| Options that are duplicated, have the effect of nullification. So for instance using the options "all |
| pralign" is equivalent to "sum rsum". |
|
|
| Defines the output reports. Default: 'sum stdout' |
| </ul> |
| <br> |
| <ul> |
|
|
| </body> |
| </html> |
|
|
