diff --git a/README.md b/README.md
index ac6eb66e..39e46cc3 100644
--- a/README.md
+++ b/README.md
@@ -239,6 +239,8 @@ You can listen to the samples and download pretrained models from the link to ou
 | [csd_english_hifigan.v1](https://drive.google.com/open?id=1NACjfBqmaecwh4dZMl714RukEkV8XLAi)                 | [link](https://github.com/kan-bayashi/ParallelWaveGAN/blob/master/egs/csd/voc1/conf/hifigan.v1.yaml)                        | EN    | 24k     | 80-7600        | 2048 / 300 / 1200    | 300k    |
 | [csd_korean_hifigan.v1](https://drive.google.com/open?id=1BGxIoRg4VgXcX0G-4Dwea030-qQ_Ynyp)                  | [link](https://github.com/kan-bayashi/ParallelWaveGAN/blob/master/egs/csd/voc1/conf/hifigan.v1.yaml)                        | EN    | 24k     | 80-7600        | 2048 / 300 / 1200    | 250k    |
 | [kising_hifigan.v1](https://drive.google.com/open?id=1GGu3pW89qxmJapd0Vm1aqp6lqgZARLO9)                      | [link](https://github.com/kan-bayashi/ParallelWaveGAN/blob/master/egs/kising/voc1/conf/hifigan.v1.yaml)                     | ZH    | 24k     | 80-7600        | 2048 / 300 / 1200    | 300k    |
+| [m4singer_hifigan.v1](https://drive.google.com/open?id=1dvD6imY6p2L80tN8tr_kzqUa3M7QJtLY)                    | [link](https://github.com/kan-bayashi/ParallelWaveGAN/blob/master/egs/m4singer/voc1/conf/hifigan.v1.yaml)                 | ZH    | 24k     | 80-7600        | 2048 / 300 / 1200     | 1M      |
+
 
 
 
diff --git a/egs/m4singer/voc1/cmd.sh b/egs/m4singer/voc1/cmd.sh
new file mode 100644
index 00000000..19f34210
--- /dev/null
+++ b/egs/m4singer/voc1/cmd.sh
@@ -0,0 +1,91 @@
+# ====== 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 documentaion 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 [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="utils/run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="utils/run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="utils/run.pl"
+
+# Local machine, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="utils/stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="utils/stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="utils/stdout.pl"
+
+# "qsub" (SGE, Torque, PBS, etc.)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="utils/queue.pl"
+    export cuda_cmd="utils/queue.pl"
+    export decode_cmd="utils/queue.pl"
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by defualt for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="utils/slurm.pl"
+    export cuda_cmd="utils/slurm.pl"
+    export decode_cmd="utils/slurm.pl"
+
+elif [ "${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="utils/ssh.pl"
+    export cuda_cmd="utils/ssh.pl"
+    export decode_cmd="utils/ssh.pl"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi
diff --git a/egs/m4singer/voc1/conf/hifigan.v1.yaml b/egs/m4singer/voc1/conf/hifigan.v1.yaml
new file mode 100644
index 00000000..cca0028b
--- /dev/null
+++ b/egs/m4singer/voc1/conf/hifigan.v1.yaml
@@ -0,0 +1,180 @@
+# This is the configuration file for LibriTTS dataset.
+# This configuration is based on HiFiGAN V1, which is
+# an official configuration. But I found that the optimizer
+# setting does not work well with my implementation.
+# So I changed optimizer settings as follows:
+# - AdamW -> Adam
+# - betas: [0.8, 0.99] -> betas: [0.5, 0.9]
+# - Scheduler: ExponentialLR -> MultiStepLR
+# To match the shift size difference, the upsample scales
+# is also modified from the original 256 shift setting.
+
+###########################################################
+#                FEATURE EXTRACTION SETTING               #
+###########################################################
+sampling_rate: 24000     # Sampling rate.
+fft_size: 2048           # FFT size.
+hop_size: 300            # Hop size.
+win_length: 1200         # Window length.
+                         # If set to null, it will be the same as fft_size.
+window: "hann"           # Window function.
+num_mels: 80             # Number of mel basis.
+fmin: 80                 # Minimum freq in mel basis calculation.
+fmax: 7600               # Maximum frequency in mel basis calculation.
+global_gain_scale: 1.0   # Will be multiplied to all of waveform.
+trim_silence: false      # Whether to trim the start and end of silence.
+trim_threshold_in_db: 20 # Need to tune carefully if the recording is not good.
+trim_frame_size: 1024    # Frame size in trimming.
+trim_hop_size: 256       # Hop size in trimming.
+format: "hdf5"           # Feature file format. "npy" or "hdf5" is supported.
+
+###########################################################
+#         GENERATOR NETWORK ARCHITECTURE SETTING          #
+###########################################################
+generator_type: HiFiGANGenerator
+generator_params:
+    in_channels: 80                       # Number of input channels.
+    out_channels: 1                       # Number of output channels.
+    channels: 512                         # Number of initial channels.
+    kernel_size: 7                        # Kernel size of initial and final conv layers.
+    upsample_scales: [5, 5, 4, 3]         # Upsampling scales.
+    upsample_kernel_sizes: [10, 10, 8, 6] # Kernel size for upsampling layers.
+    resblock_kernel_sizes: [3, 7, 11]     # Kernel size for residual blocks.
+    resblock_dilations:                   # Dilations for residual blocks.
+        - [1, 3, 5]
+        - [1, 3, 5]
+        - [1, 3, 5]
+    use_additional_convs: true            # Whether to use additional conv layer in residual blocks.
+    bias: true                            # Whether to use bias parameter in conv.
+    nonlinear_activation: "LeakyReLU"     # Nonlinear activation type.
+    nonlinear_activation_params:          # Nonlinear activation paramters.
+        negative_slope: 0.1
+    use_weight_norm: true                 # Whether to apply weight normalization.
+
+###########################################################
+#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
+###########################################################
+discriminator_type: HiFiGANMultiScaleMultiPeriodDiscriminator
+discriminator_params:
+    scales: 3                              # Number of multi-scale discriminator.
+    scale_downsample_pooling: "AvgPool1d"  # Pooling operation for scale discriminator.
+    scale_downsample_pooling_params:
+        kernel_size: 4                     # Pooling kernel size.
+        stride: 2                          # Pooling stride.
+        padding: 2                         # Padding size.
+    scale_discriminator_params:
+        in_channels: 1                     # Number of input channels.
+        out_channels: 1                    # Number of output channels.
+        kernel_sizes: [15, 41, 5, 3]       # List of kernel sizes.
+        channels: 128                      # Initial number of channels.
+        max_downsample_channels: 1024      # Maximum number of channels in downsampling conv layers.
+        max_groups: 16                     # Maximum number of groups in downsampling conv layers.
+        bias: true
+        downsample_scales: [4, 4, 4, 4, 1] # Downsampling scales.
+        nonlinear_activation: "LeakyReLU"  # Nonlinear activation.
+        nonlinear_activation_params:
+            negative_slope: 0.1
+    follow_official_norm: true             # Whether to follow the official norm setting.
+    periods: [2, 3, 5, 7, 11]              # List of period for multi-period discriminator.
+    period_discriminator_params:
+        in_channels: 1                     # Number of input channels.
+        out_channels: 1                    # Number of output channels.
+        kernel_sizes: [5, 3]               # List of kernel sizes.
+        channels: 32                       # Initial number of channels.
+        downsample_scales: [3, 3, 3, 3, 1] # Downsampling scales.
+        max_downsample_channels: 1024      # Maximum number of channels in downsampling conv layers.
+        bias: true                         # Whether to use bias parameter in conv layer."
+        nonlinear_activation: "LeakyReLU"  # Nonlinear activation.
+        nonlinear_activation_params:       # Nonlinear activation paramters.
+            negative_slope: 0.1
+        use_weight_norm: true              # Whether to apply weight normalization.
+        use_spectral_norm: false           # Whether to apply spectral normalization.
+
+###########################################################
+#                   STFT LOSS SETTING                     #
+###########################################################
+use_stft_loss: false                 # Whether to use multi-resolution STFT loss.
+use_mel_loss: true                   # Whether to use Mel-spectrogram loss.
+mel_loss_params:
+    fs: 24000
+    fft_size: 2048
+    hop_size: 300
+    win_length: 1200
+    window: "hann"
+    num_mels: 80
+    fmin: 0
+    fmax: 12000
+    log_base: null
+generator_adv_loss_params:
+    average_by_discriminators: false # Whether to average loss by #discriminators.
+discriminator_adv_loss_params:
+    average_by_discriminators: false # Whether to average loss by #discriminators.
+use_feat_match_loss: true
+feat_match_loss_params:
+    average_by_discriminators: false # Whether to average loss by #discriminators.
+    average_by_layers: false         # Whether to average loss by #layers in each discriminator.
+    include_final_outputs: false     # Whether to include final outputs in feat match loss calculation.
+
+###########################################################
+#               ADVERSARIAL LOSS SETTING                  #
+###########################################################
+lambda_aux: 45.0       # Loss balancing coefficient for STFT loss.
+lambda_adv: 1.0        # Loss balancing coefficient for adversarial loss.
+lambda_feat_match: 2.0 # Loss balancing coefficient for feat match loss..
+
+###########################################################
+#                  DATA LOADER SETTING                    #
+###########################################################
+batch_size: 16              # Batch size.
+batch_max_steps: 8400       # Length of each audio in batch. Make sure dividable by hop_size.
+pin_memory: true            # Whether to pin memory in Pytorch DataLoader.
+num_workers: 2              # Number of workers in Pytorch DataLoader.
+remove_short_samples: false # Whether to remove samples the length of which are less than batch_max_steps.
+allow_cache: false          # Whether to allow cache in dataset. If true, it requires cpu memory.
+
+###########################################################
+#             OPTIMIZER & SCHEDULER SETTING               #
+###########################################################
+generator_optimizer_type: Adam
+generator_optimizer_params:
+    lr: 2.0e-4
+    betas: [0.5, 0.9]
+    weight_decay: 0.0
+generator_scheduler_type: MultiStepLR
+generator_scheduler_params:
+    gamma: 0.5
+    milestones:
+        - 200000
+        - 400000
+        - 600000
+        - 800000
+generator_grad_norm: -1
+discriminator_optimizer_type: Adam
+discriminator_optimizer_params:
+    lr: 2.0e-4
+    betas: [0.5, 0.9]
+    weight_decay: 0.0
+discriminator_scheduler_type: MultiStepLR
+discriminator_scheduler_params:
+    gamma: 0.5
+    milestones:
+        - 200000
+        - 400000
+        - 600000
+        - 800000
+discriminator_grad_norm: -1
+
+###########################################################
+#                    INTERVAL SETTING                     #
+###########################################################
+generator_train_start_steps: 1     # Number of steps to start to train discriminator.
+discriminator_train_start_steps: 0 # Number of steps to start to train discriminator.
+train_max_steps: 2500000           # Number of training steps.
+save_interval_steps: 10000         # Interval steps to save checkpoint.
+eval_interval_steps: 1000          # Interval steps to evaluate the network.
+log_interval_steps: 100            # Interval steps to record the training log.
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_save_intermediate_results: 4  # Number of results to be saved as intermediate results.
diff --git a/egs/m4singer/voc1/conf/slurm.conf b/egs/m4singer/voc1/conf/slurm.conf
new file mode 100644
index 00000000..cefd21f0
--- /dev/null
+++ b/egs/m4singer/voc1/conf/slurm.conf
@@ -0,0 +1,12 @@
+# Default configuration
+command sbatch --export=PATH  --ntasks-per-node=1
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* --cpus-per-task $0 --ntasks-per-node=1
+option num_threads=1 --cpus-per-task 1  --ntasks-per-node=1 # Do not add anything to qsub_opts
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0
+# 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.
diff --git a/egs/m4singer/voc1/local/data_prep.py b/egs/m4singer/voc1/local/data_prep.py
new file mode 100644
index 00000000..3807056f
--- /dev/null
+++ b/egs/m4singer/voc1/local/data_prep.py
@@ -0,0 +1,118 @@
+import argparse
+import json
+import os
+import shutil
+
+import random
+import librosa
+import miditoolkit
+import numpy as np
+
+from espnet2.fileio.score_scp import SingingScoreWriter
+
+"""Generate segments according to structured annotation."""
+"""Transfer music score into 'score' format."""
+
+
+def makedir(data_url):
+    if os.path.exists(data_url):
+        shutil.rmtree(data_url)
+    os.makedirs(data_url)
+
+
+def process_utterance(
+    wavscp,
+    audio_dir,
+    wav_dumpdir,
+    segment,
+    tgt_sr=24000,
+):
+    name = segment["item_name"]
+
+    # load tempo from midi
+    uid = name.encode("unicode_escape").decode().replace("\\u", "#U")
+    song_name = uid[: uid.rindex("#")]
+    uid = uid.replace(" ", "+")
+
+    # apply bit convert, there is a known issue in direct convert in format wavscp
+    cmd = "sox {}.wav -c 1 -t wavpcm -b 16 -r {} {}/m4singer_{}.wav".format(
+        os.path.join(
+            audio_dir,
+            song_name.replace(" ", "\\ "),
+            uid.replace("+", "\\ ").split("#")[-1],
+        ),
+        tgt_sr,
+        wav_dumpdir,
+        uid,
+    )
+    os.system(cmd)
+    wavscp.write("m4singer_{} {}/m4singer_{}.wav\n".format(uid, wav_dumpdir, uid))
+
+
+def process_subset(args, set_name, data):
+    makedir(os.path.join(args.tgt_dir, set_name))
+    wavscp = open(
+        os.path.join(args.tgt_dir, set_name, "wav.scp"), "w", encoding="utf-8"
+    )
+
+    for segment in data:
+        process_utterance(
+            wavscp,
+            os.path.join(args.src_data),
+            args.wav_dumpdir,
+            segment,
+            tgt_sr=args.sr,
+        )
+
+
+def split_subset(args, meta):
+    overall_data = {}
+    item_names = []
+    for i in range(len(meta)):
+        item_name = meta[i]["item_name"]
+        overall_data[item_name] = meta[i]
+        item_names.append(item_name)
+
+    item_names = sorted(item_names)
+
+    # Refer to https://github.com/M4Singer/M4Singer
+    random.seed(1234)
+    random.shuffle(item_names)
+    valid_num, test_num = 100, 100
+
+    test_names = item_names[:test_num]
+    # NOTE(jiatong): the valid set is different from M4Singer
+    # As they include test set in the validation set
+    # but we do not.
+    valid_names = item_names[test_num : valid_num + test_num]
+    train_names = item_names[valid_num + test_num :]
+
+    data = {"tr_no_dev": [], "dev": [], "eval": []}
+
+    for key in overall_data.keys():
+        if key in test_names:
+            data["eval"].append(overall_data[key])
+        elif key in valid_names:
+            data["dev"].append(overall_data[key])
+        else:
+            data["tr_no_dev"].append(overall_data[key])
+    return data
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Prepare Data for M4Singer Database")
+    parser.add_argument("src_data", type=str, help="source data directory")
+    parser.add_argument("--tgt_dir", type=str, default="data")
+    parser.add_argument(
+        "--wav_dumpdir", type=str, help="wav dump directoyr (rebit)", default="wav_dump"
+    )
+    parser.add_argument("--sr", type=int, help="sampling rate (Hz)")
+    args = parser.parse_args()
+
+    with open(os.path.join(args.src_data, "meta.json"), "r", encoding="utf-8") as f:
+        meta = json.load(f)
+
+    data = split_subset(args, meta)
+
+    for name in ["tr_no_dev", "dev", "eval"]:
+        process_subset(args, name, data[name])
diff --git a/egs/m4singer/voc1/path.sh b/egs/m4singer/voc1/path.sh
new file mode 100644
index 00000000..b0ca27c6
--- /dev/null
+++ b/egs/m4singer/voc1/path.sh
@@ -0,0 +1,33 @@
+# cuda related
+export CUDA_HOME=/usr/local/cuda-10.0
+export LD_LIBRARY_PATH="${CUDA_HOME}/lib64:${LD_LIBRARY_PATH}"
+
+# path related
+export PRJ_ROOT="${PWD}/../../.."
+if [ -e "${PRJ_ROOT}/tools/venv/bin/activate" ]; then
+    # shellcheck disable=SC1090
+    . "${PRJ_ROOT}/tools/venv/bin/activate"
+fi
+
+# python related
+export OMP_NUM_THREADS=1
+export PYTHONIOENCODING=UTF-8
+export MPL_BACKEND=Agg
+
+# check installation
+if ! command -v parallel-wavegan-train > /dev/null; then
+    echo "Error: It seems setup is not finished." >&2
+    echo "Error: Please setup your environment by following README.md" >&2
+    return 1
+fi
+if ! command -v jq > /dev/null; then
+    echo "Error: It seems jq is not installed." >&2
+    echo "Error: Please install via \`sudo apt-get install jq\`." >&2
+    echo "Error: If you do not have sudo, please download from https://stedolan.github.io/jq/download/." >&2
+    return 1
+fi
+if ! command -v yq > /dev/null; then
+    echo "Error: It seems yq is not installed." >&2
+    echo "Error: Please install via \`pip install yq\`." >&2
+    return 1
+fi
diff --git a/egs/m4singer/voc1/run.sh b/egs/m4singer/voc1/run.sh
new file mode 100755
index 00000000..67cbecca
--- /dev/null
+++ b/egs/m4singer/voc1/run.sh
@@ -0,0 +1,205 @@
+#!/bin/bash
+
+# Copyright 2020 Tomoki Hayashi
+#  MIT License (https://opensource.org/licenses/MIT)
+
+. ./cmd.sh || exit 1;
+. ./path.sh || exit 1;
+
+# basic settings
+stage=1        # stage to start
+stop_stage=100 # stage to stop
+verbose=1      # verbosity level (lower is less info)
+n_gpus=1       # number of gpus in training
+n_jobs=4       # number of parallel jobs in feature extraction
+
+# NOTE(kan-bayashi): renamed to conf to avoid conflict in parse_options.sh
+conf=conf/hifigan.v1.yaml
+
+# directory path setting
+db_root=downloads # direcotry of unzipped m4singer
+         # details refer to https://m4singer.github.io/
+dumpdir=dump # directory to dump features
+wav_dumpdir=wav_dump # directory to dump wav
+
+
+# training related setting
+tag=""     # tag for directory to save model
+resume=""  # checkpoint path to resume training
+           # (e.g. <path>/<to>/checkpoint-10000steps.pkl)
+pretrain="" # checkpoint path to load pretrained parameters
+            # (e.g. ../../jsut/<path>/<to>/checkpoint-400000steps.pkl)
+
+# decoding related setting
+checkpoint="" # checkpoint path to be used for decoding
+              # if not provided, the latest one will be used
+              # (e.g. <path>/<to>/checkpoint-400000steps.pkl)
+
+# shellcheck disable=SC1091
+. utils/parse_options.sh || exit 1;
+
+train_set=tr_no_dev
+dev_set=dev
+eval_set="eval"
+
+set -euo pipefail
+
+if [ "${stage}" -le 0 ] && [ "${stop_stage}" -ge 0 ]; then
+    echo "Stage 0: Data preparation"
+
+    python local/data_prep.py ${db_root}/m4singer \
+        --wav_dumpdir ${wav_dumpdir} \
+	--sr 24000
+fi
+
+stats_ext=$(grep -q "hdf5" <(yq ".format" "${conf}") && echo "h5" || echo "npy")
+if [ "${stage}" -le 1 ] && [ "${stop_stage}" -ge 1 ]; then
+    echo "Stage 1: Feature extraction"
+    # extract raw features
+    pids=()
+    for name in "${train_set}" "${dev_set}" "${eval_set}"; do
+    (
+        [ ! -e "${dumpdir}/${name}/raw" ] && mkdir -p "${dumpdir}/${name}/raw"
+        echo "Feature extraction start. See the progress via ${dumpdir}/${name}/raw/preprocessing.*.log."
+        utils/make_subset_data.sh "data/${name}" "${n_jobs}" "${dumpdir}/${name}/raw"
+        ${train_cmd} JOB=1:${n_jobs} "${dumpdir}/${name}/raw/preprocessing.JOB.log" \
+            parallel-wavegan-preprocess \
+                --config "${conf}" \
+                --scp "${dumpdir}/${name}/raw/wav.JOB.scp" \
+                --dumpdir "${dumpdir}/${name}/raw/dump.JOB" \
+                --verbose "${verbose}"
+        echo "Successfully finished feature extraction of ${name} set."
+    ) &
+    pids+=($!)
+    done
+    i=0; for pid in "${pids[@]}"; do wait "${pid}" || ((++i)); done
+    [ "${i}" -gt 0 ] && echo "$0: ${i} background jobs are failed." && exit 1;
+    echo "Successfully finished feature extraction."
+
+    # calculate statistics for normalization
+    if [ -z "${pretrain}" ]; then
+        # calculate statistics for normalization
+        echo "Statistics computation start. See the progress via ${dumpdir}/${train_set}/compute_statistics.log."
+        ${train_cmd} "${dumpdir}/${train_set}/compute_statistics.log" \
+            parallel-wavegan-compute-statistics \
+                --config "${conf}" \
+                --rootdir "${dumpdir}/${train_set}/raw" \
+                --dumpdir "${dumpdir}/${train_set}" \
+                --verbose "${verbose}"
+        echo "Successfully finished calculation of statistics."
+    else
+        echo "Use statistics of pretrained model. Skip statistics computation."
+        cp "$(dirname "${pretrain}")/stats.${stats_ext}" "${dumpdir}/${train_set}"
+    fi
+
+    # normalize and dump them
+    pids=()
+    for name in "${train_set}" "${dev_set}" "${eval_set}"; do
+    (
+        [ ! -e "${dumpdir}/${name}/norm" ] && mkdir -p "${dumpdir}/${name}/norm"
+        echo "Nomalization start. See the progress via ${dumpdir}/${name}/norm/normalize.*.log."
+        ${train_cmd} JOB=1:${n_jobs} "${dumpdir}/${name}/norm/normalize.JOB.log" \
+            parallel-wavegan-normalize \
+                --config "${conf}" \
+                --stats "${dumpdir}/${train_set}/stats.${stats_ext}" \
+                --rootdir "${dumpdir}/${name}/raw/dump.JOB" \
+                --dumpdir "${dumpdir}/${name}/norm/dump.JOB" \
+                --verbose "${verbose}"
+        echo "Successfully finished normalization of ${name} set."
+    ) &
+    pids+=($!)
+    done
+    i=0; for pid in "${pids[@]}"; do wait "${pid}" || ((++i)); done
+    [ "${i}" -gt 0 ] && echo "$0: ${i} background jobs are failed." && exit 1;
+    echo "Successfully finished normalization."
+fi
+
+if [ -z "${tag}" ]; then
+    expdir="exp/${train_set}_$(basename "${conf}" .yaml)"
+    if [ -n "${pretrain}" ]; then
+        pretrain_tag=$(basename "$(dirname "${pretrain}")")
+        expdir+="_${pretrain_tag}"
+    fi
+else
+    expdir="exp/${train_set}_${tag}"
+fi
+if [ "${stage}" -le 2 ] && [ "${stop_stage}" -ge 2 ]; then
+    echo "Stage 2: Network training"
+    [ ! -e "${expdir}" ] && mkdir -p "${expdir}"
+    cp "${dumpdir}/${train_set}/stats.${stats_ext}" "${expdir}"
+    if [ "${n_gpus}" -gt 1 ]; then
+        train="python -m parallel_wavegan.distributed.launch --nproc_per_node ${n_gpus} -c parallel-wavegan-train"
+    else
+        train="parallel-wavegan-train"
+    fi
+    echo "Training start. See the progress via ${expdir}/train.log."
+    ${cuda_cmd} --gpu "${n_gpus}" "${expdir}/train.log" \
+        ${train} \
+            --config "${conf}" \
+            --train-dumpdir "${dumpdir}/${train_set}/norm" \
+            --dev-dumpdir "${dumpdir}/${dev_set}/norm" \
+            --outdir "${expdir}" \
+            --resume "${resume}" \
+            --pretrain "${pretrain}" \
+            --verbose "${verbose}"
+    echo "Successfully finished training."
+fi
+
+if [ "${stage}" -le 3 ] && [ "${stop_stage}" -ge 3 ]; then
+    echo "Stage 3: Network decoding"
+    # shellcheck disable=SC2012
+    [ -z "${checkpoint}" ] && checkpoint="$(ls -dt "${expdir}"/*.pkl | head -1 || true)"
+    outdir="${expdir}/wav/$(basename "${checkpoint}" .pkl)"
+    pids=()
+    for name in "${dev_set}" "${eval_set}"; do
+    (
+        [ ! -e "${outdir}/${name}" ] && mkdir -p "${outdir}/${name}"
+        [ "${n_gpus}" -gt 1 ] && n_gpus=1
+        echo "Decoding start. See the progress via ${outdir}/${name}/decode.log."
+        ${cuda_cmd} --gpu "${n_gpus}" "${outdir}/${name}/decode.log" \
+            parallel-wavegan-decode \
+                --dumpdir "${dumpdir}/${name}/norm" \
+                --checkpoint "${checkpoint}" \
+                --outdir "${outdir}/${name}" \
+                --verbose "${verbose}"
+        echo "Successfully finished decoding of ${name} set."
+    ) &
+    pids+=($!)
+    done
+    i=0; for pid in "${pids[@]}"; do wait "${pid}" || ((++i)); done
+    [ "${i}" -gt 0 ] && echo "$0: ${i} background jobs are failed." && exit 1;
+    echo "Successfully finished decoding."
+fi
+
+
+if [ "${stage}" -le 4 ] && [ "${stop_stage}" -ge 4 ]; then
+    echo "Stage 4: Obejctive evaluation"
+    for dset in "${dev_set}" "${eval_set}"; do
+        _data="data/${dset}"
+        _gt_wavscp="${_data}/wav.scp"
+        # shellcheck disable=SC2012
+        [ -z "${checkpoint}" ] && checkpoint="$(ls -dt "${expdir}"/*.pkl | head -1 || true)"
+        _dir="${expdir}/wav/$(basename "${checkpoint}" .pkl)"
+        _gen_wavdir="${_dir}/${dset}"
+
+        # Objective Evaluation - MCD
+        echo "Begin Scoring for MCD metrics on ${dset}, results are written under ${_dir}/${dset}/MCD_res"
+        mkdir -p "${_dir}/${dset}/MCD_res"
+        python -m parallel_wavegan.bin.evaluate_mcd \
+            --gen_wavdir_or_wavscp "${_gen_wavdir}" \
+            --gt_wavdir_or_wavscp "${_gt_wavscp}" \
+            --outdir "${_dir}/${dset}/MCD_res"
+
+        # Objective Evaluation - log-F0 RMSE & Semitone ACC & VUV Error Rate
+        echo "Begin Scoring for F0 related metrics on ${dset}, results are written under ${_dir}/${dset}/F0_res"
+        mkdir -p "${_dir}/${dset}/F0_res"
+        python -m parallel_wavegan.bin.evaluate_f0 \
+            --gen_wavdir_or_wavscp "${_gen_wavdir}" \
+            --gt_wavdir_or_wavscp "${_gt_wavscp}" \
+            --outdir "${_dir}/${dset}/F0_res"
+
+    done
+    echo "Successfully finished objective evaluation."
+fi
+
+echo "Finished."
diff --git a/egs/m4singer/voc1/utils b/egs/m4singer/voc1/utils
new file mode 120000
index 00000000..973afe67
--- /dev/null
+++ b/egs/m4singer/voc1/utils
@@ -0,0 +1 @@
+../../../utils
\ No newline at end of file
diff --git a/parallel_wavegan/models/parallel_wavegan.py b/parallel_wavegan/models/parallel_wavegan.py
index 0ebbd9e8..525c6364 100644
--- a/parallel_wavegan/models/parallel_wavegan.py
+++ b/parallel_wavegan/models/parallel_wavegan.py
@@ -195,9 +195,7 @@ def _apply_weight_norm(m):
         self.apply(_apply_weight_norm)
 
     @staticmethod
-    def _get_receptive_field_size(
-        layers, stacks, kernel_size, dilation=lambda x: 2**x
-    ):
+    def _get_receptive_field_size(layers, stacks, kernel_size, dilation=lambda x: 2**x):
         assert layers % stacks == 0
         layers_per_cycle = layers // stacks
         dilations = [dilation(i % layers_per_cycle) for i in range(layers)]