WIP: SAD and Diarization

egs/ami/s5b/conf/segmentation_speech.conf

@@ -0,0 +1,14 @@
+# General segmentation options
+pad_length=20          # Pad speech segments by this many frames on either side
+max_relabel_length=10  # Maximum duration of speech that will be removed as part
+                       # of smoothing process. This is only if there are no other
+                       # speech segments nearby.
+max_intersegment_length=30  # Merge nearby speech segments if the silence
+                            # between them is less than this many frames.
+post_pad_length=10        # Pad speech segments by this many frames on either side
+                          # after the merging process using max_intersegment_length
+max_segment_length=1000   # Segments that are longer than this are split into
+                          # overlapping frames.
+overlap_length=250        # Overlapping frames when segments are split.
+                          # See the above option.
+min_silence_length=20     # Min silence length at which to split very long segments

egs/ami/s5b/local/ami_normalize_transcripts.pl

@@ -0,0 +1,129 @@
+#!/usr/bin/env perl
+
+# Copyright 2014  University of Edinburgh (Author: Pawel Swietojanski)
+#           2016  Vimal Manohar
+
+# The script - based on punctuation times - splits segments longer than #words (input parameter)
+# and produces bit more more normalised form of transcripts, as follows
+# MeetID Channel Spkr stime etime transcripts 
+
+#use List::MoreUtils 'indexes';
+use strict;
+use warnings;
+
+sub normalise_transcripts;
+
+sub merge_hashes {
+   my ($h1, $h2) = @_;
+   my %hash1 = %$h1; my %hash2 = %$h2;
+   foreach my $key2 ( keys %hash2 ) {
+      if( exists $hash1{$key2} ) {
+         warn "Key [$key2] is in both hashes!";
+         next;
+      } else {
+        $hash1{$key2} = $hash2{$key2};
+      }
+   }
+   return %hash1;
+}
+
+sub print_hash {
+   my ($h) = @_;
+   my %hash = %$h;
+   foreach my $k (sort keys %hash) {
+      print "$k : $hash{$k}\n";
+   }
+}
+
+sub get_name {
+  #no warnings;
+  my $sname = sprintf("%07d_%07d", $_[0]*100, $_[1]*100) || die 'Input undefined!';
+  #use warnings;
+  return $sname;
+}
+
+sub split_on_comma {
+
+   my ($text, $comma_times, $btime, $etime, $max_words_per_seg)= @_;
+   my %comma_hash = %$comma_times;
+
+   print "Btime, Etime : $btime, $etime\n";
+
+   my $stime = ($etime+$btime)/2; #split time
+   my $skey = "";
+   my $otime = $btime;
+   foreach my $k (sort {$comma_hash{$a} cmp $comma_hash{$b} } keys %comma_hash) {
+      print "Key : $k : $comma_hash{$k}\n";
+      my $ktime = $comma_hash{$k};
+      if ($ktime==$btime) { next; }
+      if ($ktime==$etime) { last; }
+      if (abs($stime-$ktime)/2<abs($stime-$otime)/2) {
+         $otime = $ktime;
+         $skey = $k;
+      }
+   }
+
+   my %transcripts = ();
+
+   if (!($skey =~ /[\,][0-9]+/)) {
+      print "Cannot split into less than $max_words_per_seg words! Leaving : $text\n";
+      $transcripts{get_name($btime, $etime)}=$text;
+      return %transcripts;
+   }   
+
+   print "Splitting $text on $skey at time $otime (stime is $stime)\n";  
+   my @utts1 = split(/$skey\s+/, $text);
+   for (my $i=0; $i<=$#utts1; $i++) {
+     my $st = $btime;
+     my $et = $comma_hash{$skey};
+     if ($i>0) { 
+        $st=$comma_hash{$skey}; 
+        $et = $etime; 
+     }
+     my (@utts) = split (' ', $utts1[$i]);
+     if ($#utts < $max_words_per_seg) {
+        my $nm = get_name($st, $et);
+        print "SplittedOnComma[$i]: $nm : $utts1[$i]\n";
+        $transcripts{$nm} = $utts1[$i];
+     } else {
+        print 'Continue splitting!';
+        my %transcripts2 = split_on_comma($utts1[$i], \%comma_hash, $st, $et, $max_words_per_seg);
+        %transcripts = merge_hashes(\%transcripts, \%transcripts2);
+     }
+   }
+   return %transcripts;
+}
+
+sub normalise_transcripts {
+   my $text = $_;
+
+   #DO SOME ROUGH AND OBVIOUS PRELIMINARY NORMALISATION, AS FOLLOWS
+   #remove the remaining punctation labels e.g. some text ,0 some text ,1
+   $text =~ s/[\.\,\?\!\:][0-9]+//g;
+   #there are some extra spurious puncations without spaces, e.g. UM,I, replace with space
+   $text =~ s/[A-Z']+,[A-Z']+/ /g;
+   #split words combination, ie. ANTI-TRUST to ANTI TRUST (None of them appears in cmudict anyway)
+   #$text =~ s/(.*)([A-Z])\s+(\-)(.*)/$1$2$3$4/g;
+   $text =~ s/\-/ /g;
+   #substitute X_M_L with X. M. L. etc.
+   $text =~ s/\_/. /g;
+   #normalise and trim spaces
+   $text =~ s/^\s*//g;
+   $text =~ s/\s*$//g;
+   $text =~ s/\s+/ /g;
+   #some transcripts are empty with -, nullify (and ignore) them
+   $text =~ s/^\-$//g;
+   $text =~ s/\s+\-$//;
+   # apply few exception for dashed phrases, Mm-Hmm, Uh-Huh, etc. those are frequent in AMI
+   # and will be added to dictionary
+   $text =~ s/MM HMM/MM\-HMM/g;
+   $text =~ s/UH HUH/UH\-HUH/g;
+
+   return $text;
+}
+
+while(<>) {
+  chomp;
+  print normalise_transcripts($_) . "\n";
+}
+

egs/ami/s5b/local/chain/run_decode.sh

@@ -0,0 +1,131 @@
+#!/bin/bash
+
+# Copyright 2016  Vimal Manohar
+# Apache 2.0.
+
+set -e 
+set -o pipefail
+set -u
+
+stage=-1
+decode_stage=1
+
+mic=ihm
+use_ihm_ali=false
+exp_name=tdnn
+
+nj=20
+
+cleanup_affix=
+graph_dir=
+
+decode_set=dev
+decode_suffix=
+
+extractor=
+use_ivectors=true
+use_offline_ivectors=false
+frames_per_chunk=50
+
+scoring_opts=
+
+. path.sh
+. cmd.sh
+
+. parse_options.sh
+
+new_mic=$mic
+if [ $use_ihm_ali == "true" ]; then
+  new_mic=${mic}_cleanali
+fi
+
+dir=exp/$new_mic/chain${cleanup_affix:+_$cleanup_affix}/${exp_name}
+
+if [ $stage -le -1 ]; then
+  mfccdir=mfcc_${mic}
+  if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $mfccdir/storage ]; then
+    utils/create_split_dir.pl /export/b0{1,2,3,4}/$USER/kaldi-data/egs/ami-$mic-$(date +'%m_%d_%H_%M')/s5/$mfccdir/storage $mfccdir/storage
+  fi
+
+  steps/make_mfcc.sh --nj $nj --mfcc-config conf/mfcc.conf \
+    --cmd "$train_cmd" data/$mic/${decode_set} exp/make_${mic}/$decode_set $mfccdir || exit 1;
+
+  steps/compute_cmvn_stats.sh data/$mic/${decode_set} exp/make_${mic}/$mic/$decode_set $mfccdir || exit 1;
+
+  utils/fix_data_dir.sh data/$mic/${decode_set}
+fi
+
+if [ $stage -le 0 ]; then
+  mfccdir=mfcc_${mic}_hires
+  if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $mfccdir/storage ]; then
+    utils/create_split_dir.pl /export/b0{1,2,3,4}/$USER/kaldi-data/egs/ami-$mic-$(date +'%m_%d_%H_%M')/s5/$mfccdir/storage $mfccdir/storage
+  fi
+
+  utils/copy_data_dir.sh data/$mic/$decode_set data/$mic/${decode_set}_hires
+
+  steps/make_mfcc.sh --nj $nj --mfcc-config conf/mfcc_hires.conf \
+    --cmd "$train_cmd" data/$mic/${decode_set}_hires exp/make_${mic}_hires/$decode_set $mfccdir || exit 1;
+
+  steps/compute_cmvn_stats.sh data/$mic/${decode_set}_hires exp/make_${mic}_hires/$mic/$decode_set $mfccdir || exit 1;
+
+  utils/fix_data_dir.sh data/$mic/${decode_set}_hires
+fi
+
+if $use_ivectors && [ $stage -le 1 ]; then
+  if [ -z "$extractor" ]; then
+    echo "--extractor must be supplied when using ivectors"
+    exit 1
+  fi
+
+  if $use_offline_ivectors; then
+    steps/online/nnet2/extract_ivectors.sh \
+      --cmd "$train_cmd" --nj 8 \
+      data/$mic/${decode_set}_hires data/lang $extractor \
+      exp/$mic/nnet3${cleanup_affix:+_$cleanup_affix}/ivectors_offline_${decode_set} || exit 1
+  else
+    steps/online/nnet2/extract_ivectors_online.sh \
+      --cmd "$train_cmd" --nj 8 \
+      data/$mic/${decode_set}_hires $extractor \
+      exp/$mic/nnet3${cleanup_affix:+_$cleanup_affix}/ivectors_${decode_set} || exit 1
+  fi
+fi
+
+final_lm=`cat data/local/lm/final_lm`
+LM=$final_lm.pr1-7
+
+if [ -z "$graph_dir" ]; then
+  graph_dir=$dir/graph_${LM}
+  if [ $stage -le 2 ]; then
+    # Note: it might appear that this $lang directory is mismatched, and it is as
+    # far as the 'topo' is concerned, but this script doesn't read the 'topo' from
+    # the lang directory.
+    utils/mkgraph.sh --self-loop-scale 1.0 data/lang_${LM} $dir $graph_dir
+  fi
+fi
+
+nj=`cat data/$mic/${decode_set}/utt2spk|cut -d' ' -f2|sort -u|wc -l`
+
+if [ $nj -gt 50 ]; then
+  nj=50
+fi
+
+if [ "$frames_per_chunk" -ne 50 ]; then
+  decode_suffix=${decode_suffix}_cs${frames_per_chunk}
+fi
+
+if [ $stage -le 3 ]; then
+  ivector_opts=
+  if $use_ivectors; then
+    if $use_offline_ivectors; then
+      ivector_opts="--online-ivector-dir exp/$mic/nnet3${cleanup_affix:+_$cleanup_affix}/ivectors_offline_${decode_set}"
+      decode_suffix=${decode_suffix}_offline
+    else
+      ivector_opts="--online-ivector-dir exp/$mic/nnet3${cleanup_affix:+_$cleanup_affix}/ivectors_${decode_set}"
+    fi
+  fi
+  steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+    --stage $decode_stage --frames-per-chunk $frames_per_chunk \
+    --nj $nj --cmd "$decode_cmd" $ivector_opts \
+    --scoring-opts "--min-lmwt 5 --decode-mbr false $scoring_opts" \
+    $graph_dir data/$mic/${decode_set}_hires $dir/decode${decode_suffix}_${decode_set} || exit 1;
+fi