kaldi源碼分析(三)-特徵處理

特徵相關腳本分析

在以下腳本
steps/make_mfcc.sh
steps/make_mfcc_pitch.sh
steps/make_fbank.sh
steps/make_fbank_pitch.sh
steps/compute_cmvn_stats.sh
中涉及到的命令以及腳本情況：

命令行	作用

---

腳本	作用

---

steps/compute_cmvn_stats.sh

compute_cmvn_stats.sh 是爲了計算提取特徵的CMVN，即爲倒譜方差均值歸一化

---

提取特徵腳本 （steps/make_mfcc.sh steps/make_mfcc_pitch.sh steps/make_fbank.sh steps/make_fbank_pitch.sh ）

---

NOTE：以上所有腳本中所必需的文件爲wav.scp

這個腳本的輸入參數有三個：1.data/train 2exp/make_mfcc/train 3mfcc
1.中有數據預處理後的一些文件：text utt2spk wav.scp
2.中應該是要保存程序運行的日誌文件的
3.中是提取出的特徵文件
1是輸入目錄，2，3是輸出目錄

kaldi中以上腳本在進行提取特徵的過程中，存在着相似的結構。因此將以上四個腳本放在一塊進行記錄分析。
在此記錄中，使用 steps/make_mfcc_pitch.sh 進行基本分析，其腳本與其他腳本的區別僅僅在特徵提取的過程。

以下內容爲首先進行特徵提取的配置，參數的初始化以及配置文件的初始化

# Begin configuration section.
nj=4
cmd=run.pl
mfcc_config=conf/mfcc.conf
pitch_config=conf/pitch.conf
pitch_postprocess_config=
paste_length_tolerance=2
compress=true
write_utt2num_frames=false  # if true writes utt2num_frames
# End configuration section.

# 打印這個腳本的名稱以及所有的參數
echo "$0 $@"  # Print the command line for logging  

if [ -f path.sh ]; then . ./path.sh; fi
. parse_options.sh || exit 1;

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 <mfcc-dir> defaults to <data-dir>/data"
   echo "Options: "
   echo "  --mfcc-config              <mfcc-config-file>        # config passed to compute-mfcc-feats "
   echo "  --pitch-config             <pitch-config-file>       # config passed to compute-kaldi-pitch-feats "
   echo "  --pitch-postprocess-config <postprocess-config-file>  # config passed to process-kaldi-pitch-feats "
   echo "  --paste-length-tolerance   <tolerance>               # length tolerance passed to paste-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

以下腳本在進行使用的過程中，根據傳入參數的大小進行寫入數據

data=$1
if [ $# -ge 2 ]; then           # 如果參數大於等於2，就日誌就存放在第二參數中
  logdir=$2
else                            # 否則將日誌寫到文件下
  logdir=$data/log
fi
if [ $# -ge 3 ]; then           # 如果參數大於等於3
  mfcc_pitch_dir=$3
else                            # 將提取處理出來的特徵放到該文間加下
  mfcc_pitch_dir=$data/data
fi

在進行特徵提取的過程中，所需的必須的文件爲 wav.scp

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

# use "name" as part of name of the archive.
name=`basename $data`

mkdir -p $mfcc_pitch_dir || exit 1;                    # 創建mfcc特徵文件夾和log文件夾
mkdir -p $logdir || exit 1;

if [ -f $data/feats.scp ]; then                        # 如果之前就存在feats.scp文件夾的話，就建立
  mkdir -p $data/.backup
  echo "$0: moving $data/feats.scp to $data/.backup"
  mv $data/feats.scp $data/.backup
fi

scp=$data/wav.scp                 # 獲取音頻文件列表，根據該列表中的uttid以及wav的位置進行特徵提取

required="$scp $mfcc_config $pitch_config"

for f in $required; do             # 在進行特徵提取的過程中，所需的必須的文件爲 wav.scp
  if [ ! -f $f ]; then
    echo "make_mfcc_pitch.sh: no such file $f"
    exit 1;
  fi
done

# 使用validate_data_dir.sh 檢測$data裏的內容是否正確
utils/validate_data_dir.sh --no-text --no-feats $data || exit 1;   

TODO：隨後補充內容

if [ ! -z "$pitch_postprocess_config" ]; then
  postprocess_config_opt="--config=$pitch_postprocess_config";
else
  postprocess_config_opt=
fi

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

以下的內容主要爲是否使用segments文件，並且使用腳本進行模型處理，如下：

for n in $(seq $nj); do
  # the next command does nothing unless $mfcc_pitch_dir/storage/ exists, see
  # utils/create_data_link.pl for more info.
  utils/create_data_link.pl $mfcc_pitch_dir/raw_mfcc_pitch_$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
  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

  mfcc_feats="ark:extract-segments scp,p:$scp $logdir/segments.JOB ark:- | compute-mfcc-feats $vtln_opts --verbose=2 --config=$mfcc_config ark:- ark:- |"
  pitch_feats="ark,s,cs:extract-segments scp,p:$scp $logdir/segments.JOB ark:- | compute-kaldi-pitch-feats --verbose=2 --config=$pitch_config ark:- ark:- | process-kaldi-pitch-feats $postprocess_config_opt ark:- ark:- |"

  $cmd JOB=1:$nj $logdir/make_mfcc_pitch_${name}.JOB.log \
    paste-feats --length-tolerance=$paste_length_tolerance "$mfcc_feats" "$pitch_feats" ark:- \| \
    copy-feats --compress=$compress $write_num_frames_opt ark:- \
      ark,scp:$mfcc_pitch_dir/raw_mfcc_pitch_$name.JOB.ark,$mfcc_pitch_dir/raw_mfcc_pitch_$name.JOB.scp \
     || exit 1;

else
  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"
  done

  utils/split_scp.pl $scp $split_scps || exit 1;     # 使用腳本處理 wav.scp

  mfcc_feats="ark:compute-mfcc-feats $vtln_opts --verbose=2 --config=$mfcc_config scp,p:$logdir/wav_${name}.JOB.scp ark:- |"
  pitch_feats="ark,s,cs:compute-kaldi-pitch-feats --verbose=2 --config=$pitch_config scp,p:$logdir/wav_${name}.JOB.scp ark:- | process-kaldi-pitch-feats $postprocess_config_opt ark:- ark:- |"

  #最後生成的應該就是mfcc/train 中的raw_mfcc_train.1.ark raw_mfcc_train.1.scp

  $cmd JOB=1:$nj $logdir/make_mfcc_pitch_${name}.JOB.log \
    paste-feats --length-tolerance=$paste_length_tolerance "$mfcc_feats" "$pitch_feats" ark:- \| \
    copy-feats --compress=$compress $write_num_frames_opt ark:- \
      ark,scp:$mfcc_pitch_dir/raw_mfcc_pitch_$name.JOB.ark,$mfcc_pitch_dir/raw_mfcc_pitch_$name.JOB.scp \
      || exit 1;

fi

在進行特徵提取完之後，進行後續處理，如下：

if [ -f $logdir/.error.$name ]; then              # 如果出現了錯誤則打印出log中最後的錯誤信息，並且退出
  echo "Error producing mfcc & pitch features for $name:"
  tail $logdir/make_mfcc_pitch_${name}.1.log
  exit 1;
fi

# concatenate the .scp files together.            # 根據id，將所有的scp文件拼接起來輸出到 feats.scp
for n in $(seq $nj); do
  cat $mfcc_pitch_dir/raw_mfcc_pitch_$name.$n.scp || exit 1;
done > $data/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

rm $logdir/wav_${name}.*.scp  $logdir/segments.* 2>/dev/null       # 刪除過程文件

nf=`cat $data/feats.scp | wc -l`          # 輸出文件的行數
nu=`cat $data/utt2spk | wc -l`
if [ $nf -ne $nu ]; then                  # 檢測特徵的數目與音頻文件的數目是否相同
  echo "It seems not all of the feature files were successfully processed ($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 & Pitch features for $name"