run.sh
16.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
#!/bin/bash
# Copyright 2015-2016 David Snyder
# 2015 Johns Hopkins University (Author: Daniel Garcia-Romero)
# 2015 Johns Hopkins University (Author: Daniel Povey)
# 2017 Radboud University (Author: Emre Yilmaz)
# Apache 2.0.
#
# See README.txt for more info on data required.
# Results (EERs) are inline in comments below.
#
# This example script shows how to replace the GMM-UBM
# with a DNN trained for ASR.
. ./cmd.sh
. ./path.sh
set -e
mfccdir=`pwd`/mfcc
vaddir=`pwd`/mfcc
nnet=exp/nnet2_online/nnet_ms_a/final.mdl
famecorpus=./corpus
# Data preparation
if [ -d $famecorpus ] ; then
echo "Fame corpus present. OK."
elif [ -f ./fame.tar.gz ] ; then
echo "Unpacking..."
tar xzf fame.tar.gz
elif [ ! -d $famecorpus ] && [ ! -f ./fame.tar.gz ] ; then
echo "The Fame! corpus is not present. Please register here: http://www.ru.nl/clst/datasets/ "
echo " and download the corpus and put it at $famecorpus" && exit 1
fi
# Train a DNN on about 10 hours of Frisian-Dutch speech.
local/dnn/train_dnn.sh
echo "Preparing data/train.."
local/prepare_train.sh $famecorpus/SC
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Preparing data/fame_${task}_${subtask}_${sets}.."
trials_female=data/fame_${task}_${subtask}_${sets}_female/trials
trials_male=data/fame_${task}_${subtask}_${sets}_male/trials
trials=data/fame_${task}_${subtask}_${sets}/trials
local/make_fame_test.pl $famecorpus/SV data $task $subtask $sets
local/make_fame_train.pl $famecorpus/SV data $task $subtask $sets
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Preparing data/fame_${task}_${subtask}_${sets}${year}.."
trials_female=data/fame_${task}_${subtask}_${sets}${year}_female/trials
trials_male=data/fame_${task}_${subtask}_${sets}${year}_male/trials
trials=data/fame_${task}_${subtask}_${sets}${year}/trials
local/make_fame_test_year.pl $famecorpus/SV data $task $subtask $sets $year
local/make_fame_train_year.pl $famecorpus/SV data $task $subtask $sets $year
done
done
done
done
echo "Copying data/train.."
cp -r data/train data/train_dnn
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Copying data/fame_${task}_${subtask}_${sets}.."
cp -r data/fame_${task}_${subtask}_${sets}_enroll data/fame_${task}_${subtask}_${sets}_enroll_dnn
cp -r data/fame_${task}_${subtask}_${sets}_test data/fame_${task}_${subtask}_${sets}_test_dnn
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Copying data/fame_${task}_${subtask}_${sets}${year}.."
cp -r data/fame_${task}_${subtask}_${sets}${year}_enroll data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn
cp -r data/fame_${task}_${subtask}_${sets}${year}_test data/fame_${task}_${subtask}_${sets}${year}_test_dnn
done
done
done
done
# MFCC extraction
echo "Extracting MFCC features for data/train.."
steps/make_mfcc.sh --mfcc-config conf/mfcc_16k.conf --nj 100 --cmd "$train_cmd" \
data/train exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/train
steps/make_mfcc.sh --mfcc-config conf/mfcc_hires_16k.conf --nj 100 --cmd "$train_cmd" \
data/train_dnn exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/train_dnn
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Extracting MFCC features for data/fame_${task}_${subtask}_${sets}.."
steps/make_mfcc.sh --mfcc-config conf/mfcc_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_enroll exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}_enroll
steps/make_mfcc.sh --mfcc-config conf/mfcc_hires_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_enroll_dnn exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}_enroll_dnn
steps/make_mfcc.sh --mfcc-config conf/mfcc_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_test exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}_test
steps/make_mfcc.sh --mfcc-config conf/mfcc_hires_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_test_dnn exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}_test_dnn
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Extracting MFCC features for data/fame_${task}_${subtask}_${sets}${year}.."
steps/make_mfcc.sh --mfcc-config conf/mfcc_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_enroll exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}${year}_enroll
steps/make_mfcc.sh --mfcc-config conf/mfcc_hires_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn
steps/make_mfcc.sh --mfcc-config conf/mfcc_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_test exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}${year}_test
steps/make_mfcc.sh --mfcc-config conf/mfcc_hires_16k.conf --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_test_dnn exp/make_mfcc $mfccdir
utils/fix_data_dir.sh data/fame_${task}_${subtask}_${sets}${year}_test_dnn
done
done
done
done
# VAD computation
echo "Computing VAD for data/train.."
sid/compute_vad_decision.sh --nj 100 --cmd "$train_cmd" \
data/train exp/make_vad $vaddir
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Computing VAD for data/fame_${task}_${subtask}_${sets}.."
sid/compute_vad_decision.sh --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_enroll exp/make_vad $vaddir
sid/compute_vad_decision.sh --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}_test exp/make_vad $vaddir
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Computing VAD for data/fame_${task}_${subtask}_${sets}${year}.."
sid/compute_vad_decision.sh --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_enroll exp/make_vad $vaddir
sid/compute_vad_decision.sh --nj 100 --cmd "$train_cmd" \
data/fame_${task}_${subtask}_${sets}${year}_test exp/make_vad $vaddir
done
done
done
done
echo "Copying VAD for data/train.."
cp data/train/vad.scp data/train_dnn/vad.scp
cp data/train/utt2spk data/train_dnn/utt2spk
cp data/train/spk2utt data/train_dnn/spk2utt
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Copying VAD for data/fame_${task}_${subtask}_${sets}.."
cp data/fame_${task}_${subtask}_${sets}_enroll/vad.scp data/fame_${task}_${subtask}_${sets}_enroll_dnn/vad.scp
cp data/fame_${task}_${subtask}_${sets}_test/vad.scp data/fame_${task}_${subtask}_${sets}_test_dnn/vad.scp
cp data/fame_${task}_${subtask}_${sets}_enroll/utt2spk data/fame_${task}_${subtask}_${sets}_enroll_dnn/utt2spk
cp data/fame_${task}_${subtask}_${sets}_test/utt2spk data/fame_${task}_${subtask}_${sets}_test_dnn/utt2spk
cp data/fame_${task}_${subtask}_${sets}_enroll/spk2utt data/fame_${task}_${subtask}_${sets}_enroll_dnn/spk2utt
cp data/fame_${task}_${subtask}_${sets}_test/spk2utt data/fame_${task}_${subtask}_${sets}_test_dnn/spk2utt
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Copying VAD for data/fame_${task}_${subtask}_${sets}${year}.."
cp data/fame_${task}_${subtask}_${sets}${year}_enroll/vad.scp data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn/vad.scp
cp data/fame_${task}_${subtask}_${sets}${year}_test/vad.scp data/fame_${task}_${subtask}_${sets}${year}_test_dnn/vad.scp
cp data/fame_${task}_${subtask}_${sets}${year}_enroll/utt2spk data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn/utt2spk
cp data/fame_${task}_${subtask}_${sets}${year}_test/utt2spk data/fame_${task}_${subtask}_${sets}${year}_test_dnn/utt2spk
cp data/fame_${task}_${subtask}_${sets}${year}_enroll/spk2utt data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn/spk2utt
cp data/fame_${task}_${subtask}_${sets}${year}_test/spk2utt data/fame_${task}_${subtask}_${sets}${year}_test_dnn/spk2utt
done
done
done
done
# Train UBM and i-vector extractor
echo "Training DNN-UBM and the i-vector extractor.."
sid/init_full_ubm_from_dnn.sh --cmd "$train_cmd" \
data/train data/train_dnn $nnet exp/full_ubm
sid/train_ivector_extractor_dnn.sh \
--cmd "$train_cmd" \
--min-post 0.015 \
--ivector-dim 600 \
--num-iters 5 exp/full_ubm/final.ubm $nnet \
data/train \
data/train_dnn \
exp/extractor_dnn
# Extract i-vectors.
echo "Extracting i-vectors for data/train.."
sid/extract_ivectors_dnn.sh --cmd "$train_cmd" --nj 10 exp/extractor_dnn $nnet data/train data/train_dnn exp/ivectors_train_dnn
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
echo "Extracting i-vectors for data/fame_${task}_${subtask}_${sets}"
sid/extract_ivectors_dnn.sh --cmd "$train_cmd" --nj 10 \
exp/extractor_dnn \
$nnet \
data/fame_${task}_${subtask}_${sets}_enroll \
data/fame_${task}_${subtask}_${sets}_enroll_dnn \
exp/ivectors_fame_${task}_${subtask}_${sets}_enroll_dnn
sid/extract_ivectors_dnn.sh --cmd "$train_cmd" --nj 10 \
exp/extractor_dnn \
$nnet \
data/fame_${task}_${subtask}_${sets}_test \
data/fame_${task}_${subtask}_${sets}_test_dnn \
exp/ivectors_fame_${task}_${subtask}_${sets}_test_dnn
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
echo "Extracting i-vectors for data/fame_${task}_${subtask}_${sets}${year}"
sid/extract_ivectors_dnn.sh --cmd "$train_cmd" --nj 10 \
exp/extractor_dnn \
$nnet \
data/fame_${task}_${subtask}_${sets}${year}_enroll \
data/fame_${task}_${subtask}_${sets}${year}_enroll_dnn \
exp/ivectors_fame_${task}_${subtask}_${sets}${year}_enroll_dnn
sid/extract_ivectors_dnn.sh --cmd "$train_cmd" --nj 10 \
exp/extractor_dnn \
$nnet \
data/fame_${task}_${subtask}_${sets}${year}_test \
data/fame_${task}_${subtask}_${sets}${year}_test_dnn \
exp/ivectors_fame_${task}_${subtask}_${sets}${year}_test_dnn
done
done
done
done
# Calculate i-vector means used by the scoring scripts
echo "Calculating i-vectors means.."
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
local/scoring_common.sh data/train data/fame_${task}_${subtask}_${sets}_enroll data/fame_${task}_${subtask}_${sets}_test \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_enroll_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_test_dnn
trials_female=data/fame_${task}_${subtask}_${sets}_test_female/trials
trials_male=data/fame_${task}_${subtask}_${sets}_test_male/trials
trials=data/fame_${task}_${subtask}_${sets}_test/trials
local/plda_scoring.sh data/train data/fame_${task}_${subtask}_${sets}_enroll data/fame_${task}_${subtask}_${sets}_test \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_enroll_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_test_dnn $trials local/scores_dnn_ind_pooled_${task}_${subtask}_${sets}
local/plda_scoring.sh --use-existing-models true data/train data/fame_${task}_${subtask}_${sets}_enroll_female data/fame_${task}_${subtask}_${sets}_test_female \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_enroll_dnn_female exp/ivectors_fame_${task}_${subtask}_${sets}_test_dnn_female $trials_female local/scores_dnn_ind_female_${task}_${subtask}_${sets}
local/plda_scoring.sh --use-existing-models true data/train data/fame_${task}_${subtask}_${sets}_enroll_male data/fame_${task}_${subtask}_${sets}_test_male \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}_enroll_dnn_male exp/ivectors_fame_${task}_${subtask}_${sets}_test_dnn_male $trials_male local/scores_dnn_ind_male_${task}_${subtask}_${sets}
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
local/scoring_common.sh data/train data/fame_${task}_${subtask}_${sets}${year}_enroll data/fame_${task}_${subtask}_${sets}${year}_test \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_enroll_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_test_dnn
trials_female=data/fame_${task}_${subtask}_${sets}${year}_test_female/trials
trials_male=data/fame_${task}_${subtask}_${sets}${year}_test_male/trials
trials=data/fame_${task}_${subtask}_${sets}${year}_test/trials
local/plda_scoring.sh data/train data/fame_${task}_${subtask}_${sets}${year}_enroll data/fame_${task}_${subtask}_${sets}${year}_test \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_enroll_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_test_dnn $trials local/scores_dnn_ind_pooled_${task}_${subtask}_${sets}${year}
local/plda_scoring.sh --use-existing-models true data/train data/fame_${task}_${subtask}_${sets}${year}_enroll_female data/fame_${task}_${subtask}_${sets}${year}_test_female \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_enroll_dnn_female exp/ivectors_fame_${task}_${subtask}_${sets}${year}_test_dnn_female $trials_female local/scores_dnn_ind_female_${task}_${subtask}_${sets}${year}
local/plda_scoring.sh --use-existing-models true data/train data/fame_${task}_${subtask}_${sets}${year}_enroll_male data/fame_${task}_${subtask}_${sets}${year}_test_male \
exp/ivectors_train_dnn exp/ivectors_fame_${task}_${subtask}_${sets}${year}_enroll_dnn_male exp/ivectors_fame_${task}_${subtask}_${sets}${year}_test_dnn_male $trials_male local/scores_dnn_ind_male_${task}_${subtask}_${sets}${year}
done
done
done
done
# Calculating EER
echo "Calculating EER.."
for task in complete ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
trials=data/fame_${task}_${subtask}_${sets}_test/trials
echo "DNN EER for fame_${task}_${subtask}_${sets}"
for x in ind; do
for y in female male pooled; do
echo "python local/prepare_for_eer.py $trials local/scores_dnn_${x}_${y}_${task}_${subtask}_${sets}/plda_scores"
eer=`compute-eer <(python local/prepare_for_eer.py $trials local/scores_dnn_${x}_${y}_${task}_${subtask}_${sets}/plda_scores) 2> /dev/null`
echo "${x} ${y}: $eer"
done
done
done
done
done
for task in ageing; do
for subtask in 3sec 10sec 30sec; do
for sets in eval; do
for year in _1t3 _4t10 _mt10; do
trials=data/fame_${task}_${subtask}_${sets}${year}_test/trials
echo "DNN EER for fame_${task}_${subtask}_${sets}${year}"
for x in ind; do
for y in female male pooled; do
echo "python local/prepare_for_eer.py $trials local/scores_dnn_${x}_${y}_${task}_${subtask}_${sets}${year}/plda_scores"
eer=`compute-eer <(python local/prepare_for_eer.py $trials local/scores_dnn_${x}_${y}_${task}_${subtask}_${sets}${year}/plda_scores) 2> /dev/null`
echo "${x} ${y}: $eer"
done
done
done
done
done
done