thch30 steps/make_mfcc.sh详解

这个脚本的输入参数有三个：1.data/mfcc/train 2.exp/make_mfcc/train 3.mfcc/train
1.data/mfcc/train中有数据预处理后的一些文件：phone.txt spk2utt text utt2spk wav.scp word.txt
2.exp/make_mfcc/train中应该是要保存程序运行的日志文件的
3.mfcc/train中是提取出的特征文件
1是输入目录，2，3是输出目录

#!/bin/bash

# Copyright 2012-2016  Johns Hopkins University (Author: Daniel Povey)
# Apache 2.0
# To be run from .. (one directory up from here)
# see ../run.sh for example

# Begin configuration section.
nj=4
cmd=run.pl
mfcc_config=conf/mfcc.conf
compress=true
write_utt2num_frames=false  # if true writes utt2num_frames
# End configuration section.
# 打印这个脚本的名称以及所有的参数
echo "$0 $@"  # Print the command line for logging
# 加载path.sh和parse_options.sh
if [ -f path.sh ]; then . ./path.sh; fi
. parse_options.sh || exit 1;
# 如果参数少于1或者大于3就提示使用脚本错误
if [ $# -lt 1 ] || [ $# -gt 3 ]; then
   echo "Usage: $0 [options] <data-dir> [<log-dir> [<mfcc-dir>] ]";
   echo "e.g.: $0 data/train exp/make_mfcc/train mfcc"
   echo "Note: <log-dir> defaults to <data-dir>/log, and <mfccdir> defaults to <data-dir>/data"
   echo "Options: "
   echo "  --mfcc-config <config-file>                      # config passed to compute-mfcc-feats "
   echo "  --nj <nj>                                        # number of parallel jobs"
   echo "  --cmd (utils/run.pl|utils/queue.pl <queue opts>) # how to run jobs."
   echo "  --write-utt2num-frames <true|false>     # If true, write utt2num_frames file."
   exit 1;
fi

data=$1		# data=data/mfcc/train
if [ $# -ge 2 ]; then	# 如果参数大于等于2
  logdir=$2		# logdir=exp/make_mfcc/train
else
  logdir=$data/log
fi
if [ $# -ge 3 ]; then	# 如果参数大于等于3
  mfccdir=$3		#mfccdir=mfcc/train
else
  mfccdir=$data/data
fi

# make $mfccdir an absolute pathname.
mfccdir=`perl -e '($dir,$pwd)= @ARGV; if($dir!~m:^/:) { $dir = "$pwd/$dir"; } print $dir; ' $mfccdir ${PWD}`

# use "name" as part of name of the archive.
name=`basename $data`	# data/mfcc/train输出train
# 创建mfcc特征文件夹和log文件夹
mkdir -p $mfccdir || exit 1;
mkdir -p $logdir || exit 1;
# 如果之前有执行过生成了特征信息文件则备份
if [ -f $data/feats.scp ]; then
  mkdir -p $data/.backup
  echo "$0: moving $data/feats.scp to $data/.backup"
  mv $data/feats.scp $data/.backup
fi

scp=$data/wav.scp	# 得到音频路径列表

required="$scp $mfcc_config"

for f in $required; do		# 检测wav.scp和mfcc_config.sh文件是否存在
  if [ ! -f $f ]; then
    echo "make_mfcc.sh: no such file $f"
    exit 1;
  fi
done
# 使用validate_data_dir.sh 检测$data里的内容是否正确
utils/validate_data_dir.sh --no-text --no-feats $data || exit 1;
if [ -f $data/spk2warp ]; then
  echo "$0 [info]: using VTLN warp factors from $data/spk2warp"
  vtln_opts="--vtln-map=ark:$data/spk2warp --utt2spk=ark:$data/utt2spk"
elif [ -f $data/utt2warp ]; then
  echo "$0 [info]: using VTLN warp factors from $data/utt2warp"
  vtln_opts="--vtln-map=ark:$data/utt2warp"
fi

for n in $(seq $nj); do	# 几个线程就分几个文件 .ark中存放音频mfcc特征
  # the next command does nothing unless $mfccdir/storage/ exists, see
  # utils/create_data_link.pl for more info.
  utils/create_data_link.pl $mfccdir/raw_mfcc_$name.$n.ark
done


if $write_utt2num_frames; then
  write_num_frames_opt="--write-num-frames=ark,t:$logdir/utt2num_frames.JOB"
else
  write_num_frames_opt=
fi

if [ -f $data/segments ]; then	# 如果存在segments文件则使用已有文件
  echo "$0 [info]: segments file exists: using that."

  split_segments=""
  for n in $(seq $nj); do
    split_segments="$split_segments $logdir/segments.$n"
  done

  utils/split_scp.pl $data/segments $split_segments || exit 1;
  rm $logdir/.error 2>/dev/null

  $cmd JOB=1:$nj $logdir/make_mfcc_${name}.JOB.log \
    extract-segments scp,p:$scp $logdir/segments.JOB ark:- \| \
    compute-mfcc-feats $vtln_opts --verbose=2 --config=$mfcc_config ark:- ark:- \| \
    copy-feats --compress=$compress $write_num_frames_opt ark:- \
      ark,scp:$mfccdir/raw_mfcc_$name.JOB.ark,$mfccdir/raw_mfcc_$name.JOB.scp \
     || exit 1;

else	# 我使用的时候执行此分支
  echo "$0: [info]: no segments file exists: assuming wav.scp indexed by utterance."
  split_scps=""
  for n in $(seq $nj); do
    split_scps="$split_scps $logdir/wav_${name}.$n.scp"
    # 后面是 exp/make_mfcc/train/wav_train.1.scp
  done

  utils/split_scp.pl $scp $split_scps || exit 1;	# 使用脚本处理 scp=$data/wav.scp


  # add ,p to the input rspecifier so that we can just skip over
  # utterances that have bad wave data.
	# 这里用run.pl提取特征开始
  $cmd JOB=1:$nj $logdir/make_mfcc_${name}.JOB.log \
    compute-mfcc-feats  $vtln_opts --verbose=2 --config=$mfcc_config \
     scp,p:$logdir/wav_${name}.JOB.scp ark:- \| \
      copy-feats $write_num_frames_opt --compress=$compress ark:- \
      ark,scp:$mfccdir/raw_mfcc_$name.JOB.ark,$mfccdir/raw_mfcc_$name.JOB.scp \
      || exit 1;
fi
#最后生成的应该就是mfcc/train 中的raw_mfcc_train.1.ark raw_mfcc_train.1.scp

if [ -f $logdir/.error.$name ]; then	# 如果出现了错误则打印出log中最后的错误信息
  echo "Error producing mfcc features for $name:"
  tail $logdir/make_mfcc_${name}.1.log
  exit 1;
fi

# concatenate the .scp files together.
for n in $(seq $nj); do
  cat $mfccdir/raw_mfcc_$name.$n.scp || exit 1;
done > $data/feats.scp || exit 1	# 将所有的scp文件拼接起来输出到data/mfcc/train/feats.scp

if $write_utt2num_frames; then
  for n in $(seq $nj); do
    cat $logdir/utt2num_frames.$n || exit 1;
  done > $data/utt2num_frames || exit 1
  rm $logdir/utt2num_frames.*
fi
# 删除过程文件
rm $logdir/wav_${name}.*.scp  $logdir/segments.* 2>/dev/null

nf=`cat $data/feats.scp | wc -l`	# 输出文件的行数
nu=`cat $data/utt2spk | wc -l`
if [ $nf -ne $nu ]; then	# 检测特征的数目与音频文件的数目是否相同
  echo "It seems not all of the feature files were successfully processed ($nf != $nu);"
  echo "consider using utils/fix_data_dir.sh $data"
fi

if [ $nf -lt $[$nu - ($nu/20)] ]; then
  echo "Less than 95% the features were successfully generated.  Probably a serious error."
  exit 1;
fi

echo "Succeeded creating MFCC features for $name"