Merge pull request #5246 from Emrys365/tse

Add new SE recipes: chime1/enh1, chime2/enh1, reverb/enh1, and wsj0_2mix/tse1

egs/chime4/asr1/local/find_noisy_transcripts.pl

@@ -23,7 +23,7 @@
 # dataset (represented by a file list).
 #
 
-@ARGV == 1 || die "find_transcripts.pl dot_files_flist < utterance_ids > transcripts";
+@ARGV == 1 || die "find_noisy_transcripts.pl dot_files_flist < utterance_ids > transcripts";
 $dot_flist = shift @ARGV;
 
 open(L, "<$dot_flist") || die "Opening file list of dot files: $dot_flist\n";

egs2/README.md

@@ -25,6 +25,8 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | bur_openslr80           | Burmese ASR training dataset                                                                                                     | ASR                     | BUR                   | https://openslr.org/80/                                                                                      |              |
 | catslu               	  | CATSLU-MAPS                                                                                                                      | SLU                     | CMN           	       | https://sites.google.com/view/catslu/home                                                                    |              |
 | catslu_entity        	  | CATSLU                                                                                                                           | SLU/Entity Classifi.    | CMN           	       | https://sites.google.com/view/catslu/home                                                                    |              |
+| chime1                  | The 1st CHiME Speech Separation and Recognition Challenge                                                                        | ASR/Multichannel ASR    | ENG                   | https://spandh.dcs.shef.ac.uk/chime_challenge/chime2011/                                                      |              |
+| chime2                  | The 2nd CHiME Speech Separation and Recognition Challenge                                                                        | ASR/Multichannel ASR    | ENG                   | https://spandh.dcs.shef.ac.uk/chime_challenge/chime2013/                                                      |              |
 | chime4                  | The 4th CHiME Speech Separation and Recognition Challenge                                                                        | ASR/Multichannel ASR    | ENG                   | http://spandh.dcs.shef.ac.uk/chime_challenge/chime2016/                                                      |              |
 | chime6                  | The 6th CHiME Speech Separation and Recognition Challenge                                                                        | ASR                     | ENG                   | https://chimechallenge.github.io/chime6/                                                                     |              |
 | clarity21               | The First Clarity Enhancement Challenge CEC1                                                                                     | SE                      | ENG                   | https://claritychallenge.github.io/clarity_CEC1_doc/                                                         |              |

egs2/TEMPLATE/asr1/db.sh

@@ -27,6 +27,9 @@ WSJCAM0=
 REAZONSPEECH=downloads
 REVERB=
 REVERB_OUT="${PWD}/REVERB"  # Output file path
+CHIME1=
+CHIME2_WSJ0=
+CHIME2_GRID=
 CHIME3=
 CHIME4=
 CHIME5=

egs2/chime1/enh1/cmd.sh

@@ -0,0 +1,110 @@
+# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ======
+# Usage: <cmd>.pl [options] JOB=1:<nj> <log> <command...>
+# e.g.
+#   run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB
+#
+# Options:
+#   --time <time>: Limit the maximum time to execute.
+#   --mem <mem>: Limit the maximum memory usage.
+#   -–max-jobs-run <njob>: Limit the number parallel jobs. This is ignored for non-array jobs.
+#   --num-threads <ngpu>: Specify the number of CPU core.
+#   --gpu <ngpu>: Specify the number of GPU devices.
+#   --config: Change the configuration file from default.
+#
+# "JOB=1:10" is used for "array jobs" and it can control the number of parallel jobs.
+# The left string of "=", i.e. "JOB", is replaced by <N>(Nth job) in the command and the log file name,
+# e.g. "echo JOB" is changed to "echo 3" for the 3rd job and "echo 8" for 8th job respectively.
+# Note that the number must start with a positive number, so you can't use "JOB=0:10" for example.
+#
+# run.pl, queue.pl, slurm.pl, and ssh.pl have unified interface, not depending on its backend.
+# These options are mapping to specific options for each backend and
+# it is configured by "conf/queue.conf" and "conf/slurm.conf" by default.
+# If jobs failed, your configuration might be wrong for your environment.
+#
+#
+# The official documentation for run.pl, queue.pl, slurm.pl, and ssh.pl:
+#   "Parallelization in Kaldi": http://kaldi-asr.org/doc/queue.html
+# =========================================================~
+
+
+# Select the backend used by run.sh from "local", "stdout", "sge", "slurm", or "ssh"
+cmd_backend='local'
+
+# Local machine, without any Job scheduling system
+if [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="run.pl"
+
+# Local machine logging to stdout and log file, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="stdout.pl"
+
+
+# "qsub" (Sun Grid Engine, or derivation of it)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="queue.pl"
+    export cuda_cmd="queue.pl"
+    export decode_cmd="queue.pl"
+
+
+# "qsub" (Torque/PBS.)
+elif [ "${cmd_backend}" = pbs ]; then
+    # The default setting is written in conf/pbs.conf.
+
+    export train_cmd="pbs.pl"
+    export cuda_cmd="pbs.pl"
+    export decode_cmd="pbs.pl"
+
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="slurm.pl"
+    export cuda_cmd="slurm.pl"
+    export decode_cmd="slurm.pl"
+
+elif [ "${cmd_backend}" = ssh ]; then
+    # You have to create ".queue/machines" to specify the host to execute jobs.
+    # e.g. .queue/machines
+    #   host1
+    #   host2
+    #   host3
+    # Assuming you can login them without any password, i.e. You have to set ssh keys.
+
+    export train_cmd="ssh.pl"
+    export cuda_cmd="ssh.pl"
+    export decode_cmd="ssh.pl"
+
+# This is an example of specifying several unique options in the JHU CLSP cluster setup.
+# Users can modify/add their own command options according to their cluster environments.
+elif [ "${cmd_backend}" = jhu ]; then
+
+    export train_cmd="queue.pl --mem 2G"
+    export cuda_cmd="queue-freegpu.pl --mem 2G --gpu 1 --config conf/queue.conf"
+    export decode_cmd="queue.pl --mem 4G"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi

egs2/chime1/enh1/conf/pbs.conf

@@ -0,0 +1,11 @@
+# Default configuration
+command qsub -V -v PATH -S /bin/bash
+option name=* -N $0
+option mem=* -l mem=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -l ncpus=$0
+option num_threads=1  # Do not add anything to qsub_opts
+option num_nodes=* -l nodes=$0:ppn=1
+default gpu=0
+option gpu=0
+option gpu=* -l ngpus=$0

egs2/chime1/enh1/conf/queue.conf

@@ -0,0 +1,12 @@
+# Default configuration
+command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64*
+option name=* -N $0
+option mem=* -l mem_free=$0,ram_free=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -pe smp $0
+option num_threads=1  # Do not add anything to qsub_opts
+option max_jobs_run=* -tc $0
+option num_nodes=* -pe mpi $0  # You must set this PE as allocation_rule=1
+default gpu=0
+option gpu=0
+option gpu=* -l gpu=$0 -q g.q

egs2/chime1/enh1/conf/slurm.conf

@@ -0,0 +1,14 @@
+# Default configuration
+command sbatch --export=PATH
+option name=* --job-name $0
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0
+option num_threads=* --cpus-per-task $0
+option num_threads=1 --cpus-per-task 1
+option num_nodes=* --nodes $0
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0 -c $0  # Recommend allocating more CPU than, or equal to the number of GPU
+# note: the --max-jobs-run option is supported as a special case
+# by slurm.pl and you don't have to handle it in the config file.

egs2/chime1/enh1/conf/tuning/train_enh_beamformer_mvdr.yaml

@@ -0,0 +1,72 @@
+optim: adam
+init: xavier_uniform
+max_epoch: 70
+batch_type: folded
+batch_size: 8
+num_workers: 4
+optim_conf:
+    lr: 1.0e-03
+    eps: 1.0e-08
+    weight_decay: 0
+patience: 4
+val_scheduler_criterion:
+- valid
+- loss
+best_model_criterion:
+-   - valid
+    - si_snr
+    - max
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 1
+encoder: stft
+encoder_conf:
+    n_fft: 512
+    hop_length: 128
+    use_builtin_complex: False
+decoder: stft
+decoder_conf:
+    n_fft: 512
+    hop_length: 128
+separator: wpe_beamformer
+separator_conf:
+    num_spk: 1
+    loss_type: mask_mse
+    use_wpe: False
+    wnet_type: blstmp
+    wlayers: 3
+    wunits: 300
+    wprojs: 320
+    wdropout_rate: 0.0
+    taps: 5
+    delay: 3
+    use_dnn_mask_for_wpe: True
+    use_beamformer: True
+    bnet_type: blstmp
+    blayers: 3
+    bunits: 512
+    bprojs: 512
+    badim: 320
+    ref_channel: 3
+    use_noise_mask: True
+    beamformer_type: mvdr_souden
+    bdropout_rate: 0.0
+
+
+criterions:
+  # The first criterion
+  - name: mse
+    conf:
+      compute_on_mask: True
+      mask_type: PSM^2
+    # the wrapper for the current criterion
+    # for single-talker case, we simplely use fixed_order wrapper
+    wrapper: fixed_order
+    wrapper_conf:
+      weight: 1.0

egs2/chime1/enh1/db.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/db.sh

egs2/chime1/enh1/enh.sh

@@ -0,0 +1 @@
+../../TEMPLATE/enh1/enh.sh

egs2/chime1/enh1/local/create_chime1_trans.pl

@@ -0,0 +1,70 @@
+#!/usr/bin/env perl
+#
+# Copyright 2015  University of Sheffield (Author: Ning Ma)
+# Apache 2.0.
+#
+# Create transcriptions for the CHIME/GRID corpus from a list of
+# file names (used as UTTERANCE-ID, e.g. s1_bgab3n)
+# It outputs lines containing UTTERANCE-ID TRANSCRIPTIONS, e.g.
+#   s1_bgab3n BIN GREEN AT B THREE NOW
+#
+# Usage: create_chime1_trans.pl train.flist
+
+use strict;
+use warnings;
+
+# Define silence label at begin/end of an utternace
+my $sil = "<SIL>";
+
+my $in_list = $ARGV[0];
+
+open my $info, $in_list or die "could not open $in_list: $!";
+
+while (my $line = <$info>) {
+  chomp($line);
+  $line =~ s/\.[^.]+$//; # Remove extension just in case
+  my @tokens = split("_", $line);
+  my @chars = split("", $tokens[1]);
+  my $trans;
+
+  if ($chars[0] eq "b") { $trans = "BIN"}
+  elsif ($chars[0] eq "l") { $trans = "LAY" }
+  elsif ($chars[0] eq "p") { $trans = "PLACE" }
+  elsif ($chars[0] eq "s") { $trans = "SET" }
+  else { $trans = "!UNKNOWN"}
+
+  if ($chars[1] eq "b") { $trans = $trans . " BLUE" }
+  elsif ($chars[1] eq "g") { $trans = $trans . " GREEN" }
+  elsif ($chars[1] eq "r") { $trans = $trans . " RED" }
+  elsif ($chars[1] eq "w") { $trans = $trans . " WHITE" }
+  else { $trans = $trans . "!UNKNOWN"}
+
+  if ($chars[2] eq "a") { $trans = $trans . " AT" }
+  elsif ($chars[2] eq "b") { $trans = $trans . " BY" }
+  elsif ($chars[2] eq "i") { $trans = $trans . " IN" }
+  elsif ($chars[2] eq "w") { $trans = $trans . " WITH" }
+  else { $trans = $trans . "!UNKNOWN"}
+
+  $trans = $trans . " " . uc($chars[3]);
+
+  if ($chars[4] eq "z") { $trans = $trans . " ZERO" }
+  elsif ($chars[4] eq "1") { $trans = $trans . " ONE" }
+  elsif ($chars[4] eq "2") { $trans = $trans . " TWO" }
+  elsif ($chars[4] eq "3") { $trans = $trans . " THREE" }
+  elsif ($chars[4] eq "4") { $trans = $trans . " FOUR" }
+  elsif ($chars[4] eq "5") { $trans = $trans . " FIVE" }
+  elsif ($chars[4] eq "6") { $trans = $trans . " SIX" }
+  elsif ($chars[4] eq "7") { $trans = $trans . " SEVEN" }
+  elsif ($chars[4] eq "8") { $trans = $trans . " EIGHT" }
+  elsif ($chars[4] eq "9") { $trans = $trans . " NINE" }
+  else { $trans = $trans . "!UNKNOWN"}
+
+  if ($chars[5] eq "a") { $trans = $trans . " AGAIN" }
+  elsif ($chars[5] eq "n") { $trans = $trans . " NOW" }
+  elsif ($chars[5] eq "p") { $trans = $trans . " PLEASE" }
+  elsif ($chars[5] eq "s") { $trans = $trans . " SOON" }
+  else { $trans = $trans . "!UNKNOWN"}
+
+  #print "$line    $sil $trans $sil\n";
+  print "$line\t$trans\n";
+}