Merge pull request #5711 from atharva253/master

ESPnet recipe for the Kinect-WSJ dataset

egs2/README.md

@@ -188,6 +188,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | wsj                     | CSR-I (WSJ0) Complete, CSR-II (WSJ1) Complete                                                                                    | ASR                     | ENG                  | https://catalog.ldc.upenn.edu/LDC93S6A,https://catalog.ldc.upenn.edu/LDC94S13A                               |              |
 | wsj0_2mix               | MERL WSJ0-mix multi-speaker dataset                                                                                              | ASR/SE                  | ENG                  | http://www.merl.com/demos/deep-clustering                                                                    |              |
 | wsj0_2mix_spatialized   | MERL WSJ0-mix multi-speaker dataset (Spatialized version)                                                                        | ASR/Multichannel ASR/SE | ENG                  | http://www.merl.com/demos/deep-clustering                                                                    |              |
+| wsj_kinect	| Kinect WSJ: Multichannel, Reverberated and Noisy Extension to the WSJ0-2mix dataset	| SE	| ENG	| https://github.com/sunits/Reverberated_WSJ_2MIX	| 	|
 | yesno                   | The "yesno" corpus                                                                                                               | ASR                     | HEB                  | http://www.openslr.org/1                                                                                     |              |
 | yoloxochitl_mixtec      | Yoloxochitl-Mixtec corpus (endangered language in central Mexico)                                                                | ASR                     | XTY                  | http://www.openslr.org/89                                                                                    |              |
 | zeroth_korean           | Zeroth-Korean                                                                                                                    | ASR                     | KOR                  | http://www.openslr.org/40                                                                                    |              |

egs2/TEMPLATE/asr1/db.sh

@@ -30,7 +30,9 @@ DSING=downloads
 ESC50=
 WSJ0=
 WSJ1=
+WSJ0_2MIX= # Path to wsj0_mix directory
 WSJCAM0=
+WSJ_KINECT=
 REAZONSPEECH=downloads
 REVERB=
 REVERB_OUT="${PWD}/REVERB"  # Output file path
@@ -39,7 +41,7 @@ CHIME2_WSJ0=
 CHIME2_GRID=
 CHIME3=
 CHIME4=
-CHIME5=
+CHIME5= # Path to CHiME5/audio directory
 CSJDATATOP=
 CSJVER=dvd  ## Set your CSJ format (dvd or usb).
             ## Usage    :
@@ -52,6 +54,7 @@ CSJVER=dvd  ## Set your CSJ format (dvd or usb).
             ## Case merl :MERL setup. Necessary directory is WAV and sdb
 CSMSC=downloads
 CSS10=
+DIHARD2= # Path to dihard2/second_dihard_challenge_dev-eleven_srcs/data/multichannel/sad directory
 HKUST1=
 HKUST2=
 HUI_ACG=downloads

egs2/wsj_kinect/enh1/README.md

@@ -0,0 +1,20 @@
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Wed Mar 20 10:56:43 EDT 2024`
+- python version: `3.9.18 (main, Sep 11 2023, 13:41:44)  [GCC 11.2.0]`
+- espnet version: `espnet 202402`
+- pytorch version: `pytorch 2.1.0`
+- Git hash: `2bcd4624d49bf3cc682796470ba7fd149bc03fa4`
+  - Commit date: `Tue Mar 19 11:00:42 2024 -0400`
+
+
+## TF-GridNetV2
+
+- config: conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8.yaml
+- pretrained model: https://huggingface.co/atharva253/tfgridnetv2_wsj_kinect
+
+|dataset|STOI|SAR|SDR|SIR|SI_SNR|
+|---|---|---|---|---|---|
+|enhanced_cv|83.40|9.90|9.30|20.08|8.74|
+|enhanced_tt|86.66|10.59|9.91|19.83|9.40|

egs2/wsj_kinect/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/wsj_kinect/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/wsj_kinect/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/wsj_kinect/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/wsj_kinect/enh1/conf/train.yaml

@@ -0,0 +1 @@
+tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8.yaml

egs2/wsj_kinect/enh1/conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128.yaml

@@ -0,0 +1,57 @@
+optim: adam
+init: xavier_uniform
+max_epoch: 150
+batch_type: folded
+batch_size: 3
+iterator_type: chunk
+chunk_length: 32000
+num_workers: 4
+optim_conf:
+    lr: 1.0e-03
+    eps: 1.0e-08
+    weight_decay: 0
+patience: 5
+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: 3
+encoder: same
+decoder: same
+separator: tfgridnetv2
+separator_conf:
+    n_srcs: 2
+    n_fft: 128
+    stride: 64
+    window: "hann"
+    n_imics: 4
+    n_layers: 6
+    lstm_hidden_units: 192
+    attn_n_head: 4
+    attn_approx_qk_dim: 512
+    emb_dim: 128
+    emb_ks: 1
+    emb_hs: 1
+    activation: "prelu"
+    eps: 1.0e-5
+
+criterions:
+  # The first criterion
+  - name: si_snr
+    conf:
+      eps: 1.0e-7
+    wrapper: pit
+    wrapper_conf:
+      weight: 1.0
+      independent_perm: True

egs2/wsj_kinect/enh1/conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_16.yaml

@@ -0,0 +1,57 @@
+optim: adam
+init: xavier_uniform
+max_epoch: 150
+batch_type: folded
+batch_size: 16
+iterator_type: chunk
+chunk_length: 32000
+num_workers: 4
+optim_conf:
+    lr: 1.0e-03
+    eps: 1.0e-08
+    weight_decay: 0
+patience: 5
+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: 3
+encoder: same
+decoder: same
+separator: tfgridnetv2
+separator_conf:
+    n_srcs: 2
+    n_fft: 128
+    stride: 64
+    window: "hann"
+    n_imics: 4
+    n_layers: 6
+    lstm_hidden_units: 192
+    attn_n_head: 4
+    attn_approx_qk_dim: 512
+    emb_dim: 128
+    emb_ks: 1
+    emb_hs: 1
+    activation: "prelu"
+    eps: 1.0e-5
+
+criterions:
+  # The first criterion
+  - name: si_snr
+    conf:
+      eps: 1.0e-7
+    wrapper: pit
+    wrapper_conf:
+      weight: 1.0
+      independent_perm: True

egs2/wsj_kinect/enh1/conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8.yaml

@@ -0,0 +1,57 @@
+optim: adam
+init: xavier_uniform
+max_epoch: 150
+batch_type: folded
+batch_size: 8
+iterator_type: chunk
+chunk_length: 32000
+num_workers: 4
+optim_conf:
+    lr: 1.0e-03
+    eps: 1.0e-08
+    weight_decay: 0
+patience: 5
+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: 3
+encoder: same
+decoder: same
+separator: tfgridnetv2
+separator_conf:
+    n_srcs: 2
+    n_fft: 128
+    stride: 64
+    window: "hann"
+    n_imics: 4
+    n_layers: 6
+    lstm_hidden_units: 192
+    attn_n_head: 4
+    attn_approx_qk_dim: 512
+    emb_dim: 128
+    emb_ks: 1
+    emb_hs: 1
+    activation: "prelu"
+    eps: 1.0e-5
+
+criterions:
+  # The first criterion
+  - name: si_snr
+    conf:
+      eps: 1.0e-7
+    wrapper: pit
+    wrapper_conf:
+      weight: 1.0
+      independent_perm: True

egs2/wsj_kinect/enh1/db.sh

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

egs2/wsj_kinect/enh1/enh.sh

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