diff --git a/egs/swbd/s5c/local/chain/run_tdnn.sh b/egs/swbd/s5c/local/chain/run_tdnn.sh
index 4a39dfb66ac..2f050be93f2 120000
--- a/egs/swbd/s5c/local/chain/run_tdnn.sh
+++ b/egs/swbd/s5c/local/chain/run_tdnn.sh
@@ -1 +1 @@
-tuning/run_tdnn_7n.sh
\ No newline at end of file
+tuning/run_tdnn_7o.sh
\ No newline at end of file
diff --git a/egs/swbd/s5c/local/chain/tuning/run_tdnn_7o.sh b/egs/swbd/s5c/local/chain/tuning/run_tdnn_7o.sh
new file mode 100755
index 00000000000..753dfc632ba
--- /dev/null
+++ b/egs/swbd/s5c/local/chain/tuning/run_tdnn_7o.sh
@@ -0,0 +1,297 @@
+#!/bin/bash
+
+
+# 7o is as 7n but with a bunch of tuning changes affecting both the structure
+# and the learning rates/l2 regularization.  Structurally the main change is
+# that we also do splicing via an extra layer whose input and output are in the
+# "small" dim (256); this increases the left and right context.  We also change
+# the orthonormal-constraint to be "floating" meaning it doesn't constrain the
+# size of the matrix (the value orthonormal-constraint=-1 is interpreted
+# specially by the code), which means we can control how fast these constrained
+# layers learn layers via l2, just like the unconstrained layers.  Also the l2
+# values were increased and the learning rates were decreased; there are
+# more epochs (6->8); and the dimension of some of the layers (the ones that
+# are subsampled and which don't receive skip-splicing) was increased from
+# 1280 to 1536.  The config is a bit messy and I'd like to find a way to
+# encapsulate things a bit better; treat this as a work in progress.
+#
+#
+#
+# local/chain/compare_wer_general.sh --rt03 tdnn7n_sp tdnn7m26o_sp
+# System                tdnn7n_sp tdnn7m26j_sp
+# WER on train_dev(tg)      12.18     11.74
+# WER on train_dev(fg)      11.12     10.69
+# WER on eval2000(tg)        14.9      14.6
+# WER on eval2000(fg)        13.5      13.1
+# WER on rt03(tg)            18.4      17.5
+# WER on rt03(fg)            16.2      15.4
+# Final train prob         -0.077    -0.070
+# Final valid prob         -0.093    -0.084
+# Final train prob (xent)        -0.994    -0.883
+# Final valid prob (xent)       -1.0194   -0.9110
+# Num-parameters               20111396  22865188
+
+
+# exp/chain/tdnn7o_sp: num-iters=525 nj=3..16 num-params=22.9M dim=40+100->6034 combine=-0.074->-0.073 (over 7) xent:train/valid[348,524,final]=(-1.20,-0.884,-0.883/-1.24,-0.918,-0.911) logprob:train/valid[348,524,final]=(-0.100,-0.071,-0.070/-0.115,-0.086,-0.084)
+
+set -e
+
+# configs for 'chain'
+stage=0
+train_stage=-10
+get_egs_stage=-10
+speed_perturb=true
+affix=7o
+suffix=
+$speed_perturb && suffix=_sp
+if [ -e data/rt03 ]; then maybe_rt03=rt03; else maybe_rt03= ; fi
+
+dir=exp/chain/tdnn${affix}${suffix}
+decode_iter=
+decode_nj=50
+
+# training options
+frames_per_eg=150,110,100
+remove_egs=false
+common_egs_dir=
+xent_regularize=0.1
+dropout_schedule='0,0@0.20,0.5@0.50,0'
+
+test_online_decoding=false  # if true, it will run the last decoding stage.
+
+# End configuration section.
+echo "$0 $@"  # Print the command line for logging
+
+. ./cmd.sh
+. ./path.sh
+. ./utils/parse_options.sh
+
+if ! cuda-compiled; then
+  cat <<EOF && exit 1
+This script is intended to be used with GPUs but you have not compiled Kaldi with CUDA
+If you want to use GPUs (and have them), go to src/, and configure and make on a machine
+where "nvcc" is installed.
+EOF
+fi
+
+# The iVector-extraction and feature-dumping parts are the same as the standard
+# nnet3 setup, and you can skip them by setting "--stage 8" if you have already
+# run those things.
+
+train_set=train_nodup$suffix
+ali_dir=exp/tri4_ali_nodup$suffix
+treedir=exp/chain/tri5_7d_tree$suffix
+lang=data/lang_chain_2y
+
+
+# if we are using the speed-perturbed data we need to generate
+# alignments for it.
+local/nnet3/run_ivector_common.sh --stage $stage \
+  --speed-perturb $speed_perturb \
+  --generate-alignments $speed_perturb || exit 1;
+
+
+if [ $stage -le 9 ]; then
+  # Get the alignments as lattices (gives the LF-MMI training more freedom).
+  # use the same num-jobs as the alignments
+  nj=$(cat exp/tri4_ali_nodup$suffix/num_jobs) || exit 1;
+  steps/align_fmllr_lats.sh --nj $nj --cmd "$train_cmd" data/$train_set \
+    data/lang exp/tri4 exp/tri4_lats_nodup$suffix
+  rm exp/tri4_lats_nodup$suffix/fsts.*.gz # save space
+fi
+
+
+if [ $stage -le 10 ]; then
+  # Create a version of the lang/ directory that has one state per phone in the
+  # topo file. [note, it really has two states.. the first one is only repeated
+  # once, the second one has zero or more repeats.]
+  rm -rf $lang
+  cp -r data/lang $lang
+  silphonelist=$(cat $lang/phones/silence.csl) || exit 1;
+  nonsilphonelist=$(cat $lang/phones/nonsilence.csl) || exit 1;
+  # Use our special topology... note that later on may have to tune this
+  # topology.
+  steps/nnet3/chain/gen_topo.py $nonsilphonelist $silphonelist >$lang/topo
+fi
+
+if [ $stage -le 11 ]; then
+  # Build a tree using our new topology. This is the critically different
+  # step compared with other recipes.
+  steps/nnet3/chain/build_tree.sh --frame-subsampling-factor 3 \
+      --context-opts "--context-width=2 --central-position=1" \
+      --cmd "$train_cmd" 7000 data/$train_set $lang $ali_dir $treedir
+fi
+
+if [ $stage -le 12 ]; then
+  echo "$0: creating neural net configs using the xconfig parser";
+
+  num_targets=$(tree-info $treedir/tree |grep num-pdfs|awk '{print $2}')
+  learning_rate_factor=$(echo "print 0.5/$xent_regularize" | python)
+  opts="l2-regularize=0.004 dropout-proportion=0.0 dropout-per-dim=true dropout-per-dim-continuous=true"
+  linear_opts="orthonormal-constraint=-1.0 l2-regularize=0.004"
+  output_opts="l2-regularize=0.002"
+
+  mkdir -p $dir/configs
+
+  cat <<EOF > $dir/configs/network.xconfig
+  input dim=100 name=ivector
+  input dim=40 name=input
+
+  # please note that it is important to have input layer with the name=input
+  # as the layer immediately preceding the fixed-affine-layer to enable
+  # the use of short notation for the descriptor
+  fixed-affine-layer name=lda input=Append(-1,0,1,ReplaceIndex(ivector, t, 0)) affine-transform-file=$dir/configs/lda.mat
+
+  # the first splicing is moved before the lda layer, so no splicing here
+  relu-batchnorm-dropout-layer name=tdnn1 $opts dim=1280
+  linear-component name=tdnn2l0 dim=256 $linear_opts input=Append(-1,0)
+  linear-component name=tdnn2l dim=256 $linear_opts input=Append(-1,0)
+  relu-batchnorm-dropout-layer name=tdnn2 $opts input=Append(0,1) dim=1280
+  linear-component name=tdnn3l dim=256 $linear_opts input=Append(-1,0)
+  relu-batchnorm-dropout-layer name=tdnn3 $opts dim=1280 input=Append(0,1)
+  linear-component name=tdnn4l0 dim=256 $linear_opts input=Append(-1,0)
+  linear-component name=tdnn4l dim=256 $linear_opts input=Append(0,1)
+  relu-batchnorm-dropout-layer name=tdnn4 $opts input=Append(0,1) dim=1280
+  linear-component name=tdnn5l dim=256 $linear_opts
+  relu-batchnorm-dropout-layer name=tdnn5 $opts dim=1280 input=Append(0, tdnn3l)
+  linear-component name=tdnn6l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn6l dim=256 $linear_opts input=Append(-3,0)
+  relu-batchnorm-dropout-layer name=tdnn6 $opts input=Append(0,3) dim=1536
+  linear-component name=tdnn7l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn7l dim=256 $linear_opts input=Append(0,3)
+  relu-batchnorm-dropout-layer name=tdnn7 $opts input=Append(0,3,tdnn6l,tdnn4l,tdnn2l) dim=1280
+  linear-component name=tdnn8l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn8l dim=256 $linear_opts input=Append(0,3)
+  relu-batchnorm-dropout-layer name=tdnn8 $opts input=Append(0,3) dim=1536
+  linear-component name=tdnn9l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn9l dim=256 $linear_opts input=Append(-3,0)
+  relu-batchnorm-dropout-layer name=tdnn9 $opts input=Append(0,3,tdnn8l,tdnn6l,tdnn5l) dim=1280
+  linear-component name=tdnn10l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn10l dim=256 $linear_opts input=Append(0,3)
+  relu-batchnorm-dropout-layer name=tdnn10 $opts input=Append(0,3) dim=1536
+  linear-component name=tdnn11l0 dim=256 $linear_opts input=Append(-3,0)
+  linear-component name=tdnn11l dim=256 $linear_opts input=Append(-3,0)
+  relu-batchnorm-dropout-layer name=tdnn11 $opts input=Append(0,3,tdnn10l,tdnn9l,tdnn7l) dim=1280
+  linear-component name=prefinal-l dim=256 $linear_opts
+
+  relu-batchnorm-layer name=prefinal-chain input=prefinal-l $opts dim=1536
+  linear-component name=prefinal-chain-l dim=256 $linear_opts
+  batchnorm-component name=prefinal-chain-batchnorm
+  output-layer name=output include-log-softmax=false dim=$num_targets $output_opts
+
+  relu-batchnorm-layer name=prefinal-xent input=prefinal-l $opts dim=1536
+  linear-component name=prefinal-xent-l dim=256 $linear_opts
+  batchnorm-component name=prefinal-xent-batchnorm
+  output-layer name=output-xent dim=$num_targets learning-rate-factor=$learning_rate_factor $output_opts
+EOF
+  steps/nnet3/xconfig_to_configs.py --xconfig-file $dir/configs/network.xconfig --config-dir $dir/configs/
+fi
+
+if [ $stage -le 13 ]; then
+  if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
+    utils/create_split_dir.pl \
+     /export/b0{5,6,7,8}/$USER/kaldi-data/egs/swbd-$(date +'%m_%d_%H_%M')/s5c/$dir/egs/storage $dir/egs/storage
+  fi
+
+#    --cmd "queue.pl --config /home/dpovey/queue_conly.conf" \
+
+
+  steps/nnet3/chain/train.py --stage $train_stage \
+    --feat.online-ivector-dir exp/nnet3/ivectors_${train_set} \
+    --feat.cmvn-opts "--norm-means=false --norm-vars=false" \
+    --chain.xent-regularize $xent_regularize \
+    --chain.leaky-hmm-coefficient 0.1 \
+    --chain.l2-regularize 0.0 \
+    --chain.apply-deriv-weights false \
+    --chain.lm-opts="--num-extra-lm-states=2000" \
+    --trainer.dropout-schedule $dropout_schedule \
+    --trainer.add-option="--optimization.memory-compression-level=2" \
+    --egs.dir "$common_egs_dir" \
+    --egs.stage $get_egs_stage \
+    --egs.opts "--frames-overlap-per-eg 0" \
+    --egs.chunk-width $frames_per_eg \
+    --trainer.num-chunk-per-minibatch 128 \
+    --trainer.frames-per-iter 1500000 \
+    --trainer.num-epochs 8 \
+    --trainer.optimization.num-jobs-initial 3 \
+    --trainer.optimization.num-jobs-final 16 \
+    --trainer.optimization.initial-effective-lrate 0.0005 \
+    --trainer.optimization.final-effective-lrate 0.00005 \
+    --trainer.max-param-change 2.0 \
+    --cleanup.remove-egs $remove_egs \
+    --feat-dir data/${train_set}_hires \
+    --tree-dir $treedir \
+    --lat-dir exp/tri4_lats_nodup$suffix \
+    --dir $dir  || exit 1;
+
+fi
+
+if [ $stage -le 14 ]; 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_sw1_tg $dir $dir/graph_sw1_tg
+fi
+
+
+graph_dir=$dir/graph_sw1_tg
+iter_opts=
+if [ ! -z $decode_iter ]; then
+  iter_opts=" --iter $decode_iter "
+fi
+if [ $stage -le 15 ]; then
+  rm $dir/.error 2>/dev/null || true
+  for decode_set in train_dev eval2000 $maybe_rt03; do
+      (
+      steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+          --nj $decode_nj --cmd "$decode_cmd" $iter_opts \
+          --online-ivector-dir exp/nnet3/ivectors_${decode_set} \
+          $graph_dir data/${decode_set}_hires \
+          $dir/decode_${decode_set}${decode_iter:+_$decode_iter}_sw1_tg || exit 1;
+      if $has_fisher; then
+          steps/lmrescore_const_arpa.sh --cmd "$decode_cmd" \
+            data/lang_sw1_{tg,fsh_fg} data/${decode_set}_hires \
+            $dir/decode_${decode_set}${decode_iter:+_$decode_iter}_sw1_{tg,fsh_fg} || exit 1;
+      fi
+      ) || touch $dir/.error &
+  done
+  wait
+  if [ -f $dir/.error ]; then
+    echo "$0: something went wrong in decoding"
+    exit 1
+  fi
+fi
+
+if $test_online_decoding && [ $stage -le 16 ]; then
+  # note: if the features change (e.g. you add pitch features), you will have to
+  # change the options of the following command line.
+  steps/online/nnet3/prepare_online_decoding.sh \
+       --mfcc-config conf/mfcc_hires.conf \
+       $lang exp/nnet3/extractor $dir ${dir}_online
+
+  rm $dir/.error 2>/dev/null || true
+  for decode_set in train_dev eval2000 $maybe_rt03; do
+    (
+      # note: we just give it "$decode_set" as it only uses the wav.scp, the
+      # feature type does not matter.
+
+      steps/online/nnet3/decode.sh --nj $decode_nj --cmd "$decode_cmd" \
+          --acwt 1.0 --post-decode-acwt 10.0 \
+         $graph_dir data/${decode_set}_hires \
+         ${dir}_online/decode_${decode_set}${decode_iter:+_$decode_iter}_sw1_tg || exit 1;
+      if $has_fisher; then
+          steps/lmrescore_const_arpa.sh --cmd "$decode_cmd" \
+            data/lang_sw1_{tg,fsh_fg} data/${decode_set}_hires \
+            ${dir}_online/decode_${decode_set}${decode_iter:+_$decode_iter}_sw1_{tg,fsh_fg} || exit 1;
+      fi
+    ) || touch $dir/.error &
+  done
+  wait
+  if [ -f $dir/.error ]; then
+    echo "$0: something went wrong in decoding"
+    exit 1
+  fi
+fi
+
+
+exit 0;
diff --git a/egs/wsj/s5/steps/libs/nnet3/xconfig/parser.py b/egs/wsj/s5/steps/libs/nnet3/xconfig/parser.py
index 6fbde1fbbcc..99911b39fb2 100644
--- a/egs/wsj/s5/steps/libs/nnet3/xconfig/parser.py
+++ b/egs/wsj/s5/steps/libs/nnet3/xconfig/parser.py
@@ -69,6 +69,7 @@
         'norm-pgru-layer' : xlayers.XconfigNormPgruLayer,
         'norm-opgru-layer' : xlayers.XconfigNormOpgruLayer,
         'renorm-component': xlayers.XconfigRenormComponent,
+        'batchnorm-component': xlayers.XconfigBatchnormComponent,
         'no-op-component': xlayers.XconfigNoOpComponent,
         'linear-component': xlayers.XconfigLinearComponent
 }
diff --git a/egs/wsj/s5/steps/libs/nnet3/xconfig/trivial_layers.py b/egs/wsj/s5/steps/libs/nnet3/xconfig/trivial_layers.py
index 63f6278d1ca..f7da8956d1c 100644
--- a/egs/wsj/s5/steps/libs/nnet3/xconfig/trivial_layers.py
+++ b/egs/wsj/s5/steps/libs/nnet3/xconfig/trivial_layers.py
@@ -16,7 +16,7 @@
 
 class XconfigRenormComponent(XconfigLayerBase):
     """This class is for parsing lines like
-     'renorm-component name=renorm input=Append(-3,0,3)'
+     'renorm-component name=renorm1 input=Append(-3,0,3)'
     which will produce just a single component, of type NormalizeComponent.
 
     Parameters of the class, and their defaults:
@@ -70,9 +70,65 @@ def _generate_config(self):
         return configs
 
 
+class XconfigBatchnormComponent(XconfigLayerBase):
+    """This class is for parsing lines like
+     'batchnorm-component name=batchnorm input=Append(-3,0,3)'
+    which will produce just a single component, of type BatchNormComponent.
+
+    Parameters of the class, and their defaults:
+      input='[-1]'             [Descriptor giving the input of the layer.]
+      target-rms=1.0           [The target RMS of the BatchNormComponent]
+    """
+    def __init__(self, first_token, key_to_value, prev_names=None):
+        XconfigLayerBase.__init__(self, first_token, key_to_value, prev_names)
+
+    def set_default_configs(self):
+        self.config = {'input': '[-1]',
+                       'target-rms': 1.0 }
+
+    def check_configs(self):
+        assert self.config['target-rms'] > 0.0
+
+    def output_name(self, auxiliary_output=None):
+        assert auxiliary_output is None
+        return self.name
+
+    def output_dim(self, auxiliary_output=None):
+        assert auxiliary_output is None
+        input_dim = self.descriptors['input']['dim']
+        return input_dim
+
+    def get_full_config(self):
+        ans = []
+        config_lines = self._generate_config()
+
+        for line in config_lines:
+            for config_name in ['ref', 'final']:
+                # we do not support user specified matrices in this layer
+                # so 'ref' and 'final' configs are the same.
+                ans.append((config_name, line))
+        return ans
+
+    def _generate_config(self):
+        # by 'descriptor_final_string' we mean a string that can appear in
+        # config-files, i.e. it contains the 'final' names of nodes.
+        input_desc = self.descriptors['input']['final-string']
+        input_dim = self.descriptors['input']['dim']
+        target_rms = self.config['target-rms']
+
+        configs = []
+        line = ('component name={0} type=BatchNormComponent dim={1} target-rms={2}'.format(
+            self.name, input_dim, target_rms))
+        configs.append(line)
+        line = ('component-node name={0} component={0} input={1}'.format(
+            self.name, input_desc))
+        configs.append(line)
+        return configs
+
+
 class XconfigNoOpComponent(XconfigLayerBase):
     """This class is for parsing lines like
-     'no-op-component name=renorm input=Append(-3,0,3)'
+     'no-op-component name=noop1 input=Append(-3,0,3)'
     which will produce just a single component, of type NoOpComponent.
 
     Parameters of the class, and their defaults:
@@ -127,7 +183,7 @@ class XconfigLinearComponent(XconfigLayerBase):
     """This class is for parsing lines like
      'linear-component name=linear1 dim=1024 input=Append(-3,0,3)'
     which will produce just a single component, of type LinearComponent, with
-    output-dim 1024 in this case, and input-dim determined by the dimention
+    output-dim 1024 in this case, and input-dim determined by the dimension
     of the input .
 
     Parameters of the class, and their defaults:
@@ -137,7 +193,7 @@ class XconfigLinearComponent(XconfigLayerBase):
     The following (shown with their effective defaults) are just passed through
     to the component's config line.
 
-      orthonormal-constraint=-1
+      orthonormal-constraint=0.0
       max-change=0.75
       l2-regularize=0.0