Merge pull request #5659 from Alexgichamba/sdsv_2021

ESPnet-SPK: add SdSV 2021 recipe

egs2/README.md

@@ -146,6 +146,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | reverb                  | REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge                                                       | ASR                     | ENG                  | https://reverb2014.dereverberation.com/                                                                      |              |
 | ru_open_stt             | Russian Open Speech To Text (STT/ASR) Dataset                                                                                    | ASR                     | RUS                  | https://github.com/snakers4/open_stt                                                                         |              |
 | ruslan                  | RUSLAN: Russian Spoken Language Corpus For Speech Synthesis                                                                      | TTS                     | RUS                  | https://ruslan-corpus.github.io/                                                                             |              |
+| sdsv21                   | SdSV 2021: Short-duration Speaker Verification (SdSV) Challenge 2021                                                        | SPK                     | 10+ Languages           | https://sdsvc.github.io/                                                                     |              |
 | seame                   | SEAME: a Mandarin-English Code-switching Speech Corpus in South-East Asia                                                        | ASR                     | ENG + CMN            | https://catalog.ldc.upenn.edu/LDC2015S04                                                                     |              |
 | sinhala                 | Sinhala speech recognition corpus                                                                                                | ASR                     | SIN                  | https://drive.google.com/file/d/17_e0JhMW4_FPxfh93foplnxb4OQp8zh3/view?usp=sharing                           |              |
 | siwis                   | SIWIS: Spoken Interaction with Interpretation in Switzerland                                                                     | TTS                     | FRA                  | https://datashare.ed.ac.uk/handle/10283/2353                                                                 |              |

egs2/TEMPLATE/spk1/db.sh

@@ -1,6 +1,9 @@
 # Set the path of your corpus
 # "downloads" means the corpus can be downloaded by the recipe automatically
 
+PUBLICDEEPMINE=downloads
+LIBRISPEECH=downloads
+COMMONVOICE16FARSI=downloads
 VOXBLINK=downloads
 VOXCELEB=downloads
 MUSAN=downloads

egs2/sdsv21/spk1/README.md

@@ -0,0 +1,14 @@
+# RESULTS
+Overall results
+
+## Test set: Vox1-O
+
+| Model (conf name) | EER(%) | minDCF | Note | HuggingFace |
+|---|---|---|---|---|
+| [conf/train_rawnet3.yaml](conf/train_rawnet3.yaml) | 1.229 | 0.08033  | | [https://huggingface.co/espnet/voxcelebs12devs_librispeech_cv16fa_rawnet3](https://huggingface.co/espnet/voxcelebs12devs_librispeech_cv16fa_rawnet3) |
+
+## Test set: Sample DeepMine
+
+| Model (conf name) | EER(%) | minDCF | Note | HuggingFace |
+|---|---|---|---|---|
+| [conf/train_rawnet3.yaml](conf/train_rawnet3.yaml) | 4.640 | 0.25994 | | [https://huggingface.co/espnet/voxcelebs12devs_librispeech_cv16fa_rawnet3](https://huggingface.co/espnet/voxcelebs12devs_librispeech_cv16fa_rawnet3) |

egs2/sdsv21/spk1/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/sdsv21/spk1/conf/decode.yaml

@@ -0,0 +1,16 @@
+# embedding extraction
+num_workers: 2
+valid_batch_size: 40
+target_duration: 8.0  # seconds
+num_eval: 2
+
+# score norm
+num_cohort_spk: 5994
+num_utt_per_spk: 20
+utt_select_sec: 2
+adaptive_cohort_size: 500
+average_spk: true
+
+# quality measure function
+qmf_dur_thresh: 6
+qmf_num_trial_per_condition: 5000

egs2/sdsv21/spk1/conf/fbank.conf

@@ -0,0 +1,2 @@
+--sample-frequency=16000
+--num-mel-bins=80

egs2/sdsv21/spk1/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/sdsv21/spk1/conf/pitch.conf

@@ -0,0 +1 @@
+--sample-frequency=16000

egs2/sdsv21/spk1/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/sdsv21/spk1/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/sdsv21/spk1/conf/train_rawnet3.yaml

@@ -0,0 +1,92 @@
+# RawNet3 reproduce recipe configuration.
+# Requires approx. 40GRAM per GPU when run with 2GPUs
+# or 20GRAM when run with 4GPUs.
+
+# Frontend
+frontend: asteroid_frontend
+frontend_conf:
+    sinc_stride: 16
+    sinc_kernel_size: 251
+    sinc_filters: 256
+    preemph_coef: 0.97
+    log_term: 0.000001
+
+# Encoder
+encoder: rawnet3
+encoder_conf:
+  model_scale: 8
+  ndim: 1024
+  output_size: 1536
+
+# Pooling
+pooling: chn_attn_stat
+
+# Projector
+projector: rawnet3
+projector_conf:
+  output_size: 192
+
+# Preprocessor
+preprocessor: spk
+preprocessor_conf:
+  target_duration: 3.0  # seconds
+  sample_rate: 16000
+  num_eval: 5
+  noise_apply_prob: 0.5
+  noise_info:
+  - [1.0, 'dump/raw/musan_speech.scp', [4, 7], [13, 20]]
+  - [1.0, 'dump/raw/musan_noise.scp', [1, 1], [0, 15]]
+  - [1.0, 'dump/raw/musan_music.scp', [1, 1], [5, 15]]
+  rir_apply_prob: 0.5
+  rir_scp: dump/raw/rirs.scp
+
+# Model config
+model_conf:
+  extract_feats_in_collect_stats: false
+
+# Loss
+loss: aamsoftmax_sc_topk
+loss_conf:
+  margin: 0.3
+  scale: 30
+  K: 3
+  mp: 0.06
+  k_top: 5
+
+# Training related
+max_epoch: 40
+num_att_plot: 0
+num_workers: 2
+cudnn_deterministic: False
+cudnn_benchmark: True
+drop_last_iter: True
+iterator_type: category
+valid_iterator_type: sequence
+shuffle_within_batch: False
+log_interval: 100
+batch_size: 128
+valid_batch_size: 40
+use_amp: False
+keep_nbest_models: 3
+grad_clip: 9999
+best_model_criterion:
+- - valid
+  - eer
+  - min
+
+# Optimizer
+optim: adam
+optim_conf:
+  lr: 0.001
+  weight_decay: 0.00005
+  amsgrad: False
+
+# Scheduler
+scheduler: CosineAnnealingWarmupRestarts
+scheduler_conf:
+  first_cycle_steps: 158760 # equal to 4 epochs
+  cycle_mult: 1.0
+  max_lr: 0.001
+  min_lr: 0.000005
+  warmup_steps: 1000
+  gamma: 0.75

egs2/sdsv21/spk1/db.sh

@@ -0,0 +1 @@
+../../TEMPLATE/spk1/db.sh