As crazyinsomniac says, move the test out of the while loop becuase you don't have the full sentence. I went ahead and made some more changes. Got rid of some variables that were not needed, some stylistic changes as well, and two uses of grep. More can be done, but that's the once over for me

#!/usr/bin/perl -w
#
# Create clusters of meeting data in a semi-unsupervised fashion
#
# parameters:
# 1) input directory
# 2) output data
####################################################################
use strict;

my $indir = shift @ARGV or die "No indir supplied";
my $outfile = shift @ARGV or die "No outfile supplied";

die "$indir not a directory!" unless -d $indir;
open(OUTPUT, ">$outfile") || die "Could not open $outfile";
die "Could not chdir $indir" unless chdir($indir);
opendir(INDIR, ".") || die "directory open of $indir failed";

# I prefer the chdir instead of using the slash for reading the filena
+mes

my @files = grep(!/^..?\z/, readdir(INDIR)); #get all the files in the
+ directory
# I'm not sure if readdir will always give you . and .. first
# See the readdir function in the docs. That's my prefered method from
+ the camel
closedir(INDIR); #just being neat

foreach my $infile (@files) { #process files until none are left
  next if -d $infile;
  open(INPUT, $infile) || die "error on file opening $infile";

  my $within_spurt=0;
  my $previous_interupt = 0;
  my @current_spurt;
  <INPUT>; # skip first line which isn't data
  while (<INPUT>) { #inner loop to create initail clustering
    my (undef, undef,
        $current_word,
        $word_in_spurt,
        $spurt_length,
        undef, undef, undef, undef,
        $primary_speaker,
        undef,
        $interupting_speakers) = split(' ');

# see if number of speakers increases and first_speaker == 0, 
# this means the spurt is interupting, not the primary speaker
  if ($primary_speaker == 0 && 
      $interupting_speakers > $previous_interupt && 
      $word_in_spurt == 1) {
    push @current_spurt, "<s> $current_word ";# start marker
    $within_spurt = 1;
    if($word_in_spurt == $spurt_length) {#only word in spurt
      push @current_spurt, "<\/s>\n";
      $within_spurt = 0;
      $interupting_speakers = 0; # the interupt is over
    }
  }
# if we are in a spurt and it is not the last word of that spurt
  elsif($within_spurt && $word_in_spurt != $spurt_length) {
    push @current_spurt, "$current_word "; #add current word
  }
# if this is the last word of a spurt
  elsif($word_in_spurt == $spurt_length && $within_spurt == 1) {
    push @current_spurt, "$current_word <\/s>\n"; #end marker
    $within_spurt = 0;
    $interupting_speakers = 0; # the interupt is over
  }
#make sure that at the end of spurts this flag is reduced
  if($word_in_spurt == $spurt_length) {
    $interupting_speakers--;
# should not be less than 0
    if($interupting_speakers < 0) { $interupting_speakers = 0; }
  }
  $previous_interupt = $interupting_speakers;
  }
  close(INPUT);

  if( grep { /\bso\b/ } @current_spurt) {;
    print STDOUT @current_spurt;
    print OUTPUT @current_spurt;
  }
}
[download]

---

---

Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!

Titles consisting of a single word are discouraged, and in most cases are disallowed outright.

Read Where should I post X? if you're not absolutely sure you're posting in the right place.

Please read these before you post! —

• How do I compose an effective node title?
• How do I post a question effectively?
• Markup in the Monastery

Posts may use any of the Perl Monks Approved HTML tags:

a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr

You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)

	For:		Use:
	&		&
	<		&lt;
	>		&gt;
	[		&#91;
	]		&#93;

Link using PerlMonks shortcuts! What shortcuts can I use for linking?

See Writeup Formatting Tips and other pages linked from there for more info.