2014-11-03 - 版本历史

2014年11月5日 (三) 08:35 Zhangzy

2014-11-05T08:35:46Z

Lyy：/* VAD */

2014-11-03T09:11:29Z

‎VAD

2014年11月3日 (一) 09:10 Lyy

2014-11-03T09:10:28Z

显示更改

Lr：/* QA */

2014-11-03T05:52:43Z

‎QA

Lr：/* QA */

2014-11-03T05:52:20Z

‎QA

Lr：/* QA */

2014-11-03T05:50:56Z

‎QA

Lr：/* Translation */

2014-11-03T05:48:53Z

‎Translation

Lr：/* RNN LM */

2014-11-03T05:47:52Z

‎RNN LM

Lr：/* Text Processing */

2014-11-03T05:43:37Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Contour ==== * NAN problem :* nan recurrence ------------------------------------------------------------...”为内容创建页面

2014-11-03T01:05:51Z

以“==Speech Processing == === AM development === ==== Contour ==== * NAN problem :* nan recurrence ------------------------------------------------------------...”为内容创建页面

新页面

==Speech Processing ==
=== AM development ===

==== Contour ====
* NAN problem
:* nan recurrence
------------------------------------------------------------
grid/atr. | Reproducible | add.
------------------------------------------------------------
grid-10 | yes |
------------------------------------------------------------
grid-12 | no | "nan" in different position
------------------------------------------------------------
grid-14 | yes |
------------------------------------------------------------
:* buy 760-GPU

==== Sparse DNN ====
* Performance improvement found when pruned slightly
* Experiments show that
* Suggest to use TIMIT / AURORA 4 for training
* HOLD

==== RNN AM====
* Initial nnet seems no very well, need to be pre-trained or test lower learn-rate.
* For AURORA4 1h/epoch, 100 epochs done.
* Using AURORA 4 short-sentence with a smaller number of targets.

====Noise training====
* First draft of the noisy training journal paper.
* Second version released.
* Paper Correction (Yinshi, Liuchao, Lin Yiye), be going.

====Drop out & Rectification & convolutive network====

* Drop out
:* dataset:wsj, testset:eval92
std | dropout0.4 | dropout0.5 | dropout0.6 | dropout0.7 | dropout0.8
-------------------------------------------------------------------------
4.5 | 5.39 | 4.80 | 4.75 | 4.36 | 4.55
:** Frame-accuarcy seems not consistent with WER.
:** Using the train-data as cv, verify the learning ability of the model.

:* AURORA4 dataset
(1) Train: train_clean
drop-retention/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
std-baseline | 6.04 | 29.91 | 27.76 | 16.37
---------------------------------------------------------------------------------------------------------
dp-0.4 | 6.61 | 29.59 | 30.12 | 19.40
---------------------------------------------------------------------------------------------------------
dp-0.5 | 6.40 | 28.07 | 27.88 | 19.88
---------------------------------------------------------------------------------------------------------
dp-0.6 | 6.36 | 26.68 | 24.85 | 18.32
---------------------------------------------------------------------------------------------------------
dp-0.7 | 6.13 | 25.53 | 23.90 | 15.69
---------------------------------------------------------------------------------------------------------
dp-0.8 | 5.94 | 24.94 | 23.67 | 15.77
---------------------------------------------------------------------------------------------------------
dp-0.9 | 5.96 | 27.30 | 25.63 | 15.46
---------------------------------------------------------------------------------------------------------

(2) Train: train_nosiy
drop-retention/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
std-baseline | 9.60 | 11.41 | 11.63 | 8.64
---------------------------------------------------------------------------------------------------------
dp-0.3 | 12.91 | 16.55 | 15.37 | 12.60
---------------------------------------------------------------------------------------------------------
dp-0.4 | 11.48 | 14.43 | 13.23 | 11.04
---------------------------------------------------------------------------------------------------------
dp-0.5 | 10.53 | 13.00 | 12.89 | 10.24
---------------------------------------------------------------------------------------------------------
dp-0.6 | 10.02 | 12.32 | 11.81 | 9.29
---------------------------------------------------------------------------------------------------------
dp-0.7 | 9.65 | 12.01 | 12.09 | 8.89
---------------------------------------------------------------------------------------------------------
dp-0.8 | 9.79 | 12.01 | 11.77 | 8.91
---------------------------------------------------------------------------------------------------------
dp-1.0 | 9.94 | 11.33 | 12.05 | 8.32
---------------------------------------------------------------------------------------------------------
:** Losing important features, enlarge the hidden-layer dim to 2048.
:** Follow the standard dnn training learn-rate to avoid the different learn-rate changing time of various DNN training.
:** Test out of known noise test-data.
:** Continue the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). (++)
:** Draft the dropout-DNN weight distribution. (++)

* Rectification
:* Still NAN error, need to debug.
1) AURORA4 -15h
(1) Train: train_clean
learn-rate/testcase(WER) | test_clean_wv1 | test_airport_wv1 | test_babble_wv1 | test_car_wv1
---------------------------------------------------------------------------------------------------------
std-baseline | 6.04 | 29.91 | 27.76 | 16.37
---------------------------------------------------------------------------------------------------------
lr0.001 | 6.28 | 30.01 | 30.26 | 20.81
---------------------------------------------------------------------------------------------------------
lr0.003 | 6.44 | 32.01 | 32.24 | 17.82
---------------------------------------------------------------------------------------------------------
lr0.005 | 6.47 | 33.49 | 34.75 | 18.15
---------------------------------------------------------------------------------------------------------
lr0.007 | 6.72 | 35.85 | 39.72 | 18.03
---------------------------------------------------------------------------------------------------------
lr-0.001_l1-0.001 | 83.19 | 98.57 | 98.84 | 97.77
---------------------------------------------------------------------------------------------------------
lr-0.001_l1-0.0001 | 7.58 | 32.94 | 34.29 | 23.42
---------------------------------------------------------------------------------------------------------
lr-0.001_l1-0.00001 | 6.21 | 29.15 | 28.24 | 19.50
---------------------------------------------------------------------------------------------------------
lr-0.001_l1-0.000001 | 6.30 | 31.91 | 29.23 | 21.52
---------------------------------------------------------------------------------------------------------
:* Change the learn-rate in the middle of the training, Modify the train_nnet.sh script(Liu Chao).
:* Using maximum learning-rate.

* MaxOut (++)

* Convolutive network (+)
:* Test more configurations

====Denoising & Farfield ASR====

* ICASSP paper submitted.
* HOLD

====VAD====

* Spike detection and removal.
* Add more silence tag "#" in pure-silence utterance text(train).
:* xEntropy model be training
:* need to test baseline.
* Sum all sil-pdf as the silence posterior probability.
:* Program done, to tune the threshold
* rearrange the ending point of the detected speech

====Speech rate training====
* Seems ROS model is superior to the normal one with faster speech
* Suggest to extract speech data of different ROS, construct a new test set(+)
* Tencent training data done

==== low resource language AM training ====
* Use Chinese NN as initial NN, change the last layer
:* Various the used Chinese trained DNN layer numbers.
:** feature_transform = 6000h_transform + 6000_N*hidden-layers
nnet.init = random (4-N)*hidden-layers + output-layer
| N / learn_rate | 0.008 | 0.001 | 0.0001 |
| baseline | 17.00(14*2h) | | |
| 4 | 17.75(9*0.6h) | 18.64 | |
| 3 | 16.85 | | |
| 2 | 16.69 | | |
| 1 | 16.87 | | |
| 0 | 16.88 | | |
:** feature_transform = uyghur_transform + 6000_N*hidden-layers
nnet.init = random (4-N)*hidden-layers + output-layer
Note: This is reproduced Yinshi's experiment
| N / learn_rate | 0.008 | 0.001 | 0.0001 |
| baseline | 17.00 | | |
| 4 | 28.23 | 30.72 | 37.32 |
| 3 | 22.40 | | |
| 2 | 19.76 | | |
| 1 | 17.41 | | |
| 0 | | | |

:** feature_transform = 6000_transform + 6000_N*hidden-layers
nnet.init = uyghur (4-N)*hidden-layers + output-layer
| N / learn_rate | 0.008 | 0.001 | 0.0001 |
| baseline | 17.00 | | |
| 4 | 17.80 | 18.55 | 21.06 |
| 3 | 16.89 | 17.64 | |
| 2 | | | |
| 1 | | | |
| 0 | | | |

* sub word unit language model is ready. on testing.
====Scoring====
* Harmonics program done, experiment to be done.
* Initial experiment shows more timber data are required

====Confidence====
* Reproduce the experiments on fisher dataset.
* Use the fisher DNN model to decode all-wsj dataset
* preparing scoring for puqiang data

===Speaker ID===
* Preparing GMM-based server.
* EER ~ 11.2% (GMM-based system)
* test different number of components; fast i-vector computing

===Emotion detection===

* Sinovoice is implementing the server

==Text Processing==
===LM development===

====Domain specific LM====
* domain lm
:* am:1400h(2.0.b) .result: xiaomi-29.43%,baiduzhidao-43.46%,baiduHi-30.02%, test-set:8ksentence(16k=>8k)
:* need to check the xiaomin-lm method and result.

* new dict.
:* weibo-data : Tencent-segment and count. get 16k words to segment again.
:* new toolkit:find method to update the new dict. can get new wordlist from sougou and get word information from baidu.

====tag LM====

* set new test
:* 1k address from dianxin. prepare to test.
:* insert the new unknown-address to test set.
:* record test set 15-sentence/person on dianxin txt.

====RNN LM====
*rnn
:* RNNLM=>ALPA
:* train RNNLM on Chinese data from jietong-data
*lstm+rnn
:* wer:6.2%(4-epoch).need to check the problem.

===Word2Vector===

====W2V based doc classification====

* Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.
* Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation
:* SSA-based local linear mapping still on running.
:* k-means classes change to 2.

* Knowledge vector started
:* format the data
:* yuanbin will continue this work with help of xingchao.

* Character to word conversion
:* prepare the task: word similarity
:* prepare the dict.

* Google word vector train
:* some ideal will discuss on weekly report.

===Translation===

* v3.0 demo released
:* still slow
:* re-segment the word using new dictionary.will use the tencent-dic about 11w.
:* check new data.

===QA===

* search method:
:* test the lucene method
:* analysis the test result
:* add IDF to test
* spell check
:* get ngram tool and make a simple demo.
:* get domain word list and pingyin tool from huilan.
* new inter will install SEMPRE

←上一版本		2014年11月3日 (一) 09:11的版本
第156行：		第156行：

	====VAD====		====VAD====
−
−	* Spike detection and removal.
−	* Sum all sil-pdf as the silence posterior probability.
−	~~:* Program done, to tune the threshold~~
−	* rearrange the ending point of the detected speech

	====Speech rate training====		====Speech rate training====

@@ 第255行： / 第255行： @@
 :* check the query method for getting lucene information and to rewrite the score method like the idf value.
 * test
-:* test the different idf vale from baidu sougou in fuzzymatch.
+:* test the different idf vale from baidu sougou in fuzzymatch.('''this week''')
-:* need to check the other 10% error
+:* need to check the other 10% error.('''this week''')
 * spell check
 :* simple demo done.
 * new inter will install SEMPRE

@@ 第248行： / 第248行： @@
 ===QA===
-* lucene Optimization(liurong)
+* lucene Optimization
-:* rewrite the method to select the 50 standard question not same template.
+:* rewrite the method to select the 50 standard question not same template.('''this week''')
-:* test the boost keyword weight and extract the synonyms word.
+:* test the boost keyword weight and extract the synonyms word.('''this week''')
-:* check the word segment for template.
+:* check the word segment for template.('''this week''')
 :* min-segment method improve the accuracy.(0.61->0.66)
 :* check the query method for getting lucene information and to rewrite the score method like the idf value.
+* test
 * spell check
 :* simple demo done.
 * new inter will install SEMPRE

@@ 第30行： / 第30行： @@
 .5 |     5.39    |    4.80    |   4.75     |  4.36      |    4.55
 :** Frame-accuarcy seems not consistent with WER.
 :** Using the train-data as cv, verify the learning ability of the model.
 :* AURORA4 dataset
-    (1) Train: train_clean
-    drop-retention/testcase(WER) | test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1
+    (1) Train: train_nosiy
-    ---------------------------------------------------------------------------------------------------------
-           std-baseline          |  6.04           |  29.91           |  27.76          |  16.37
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.4             |  6.61           |  29.59           |  30.12          |  19.40
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.5             |  6.40           |  28.07           |  27.88          |  19.88
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.6             |  6.36           |  26.68           |  24.85          |  18.32
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.7             |  6.13           |  25.53           |  23.90          |  15.69
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.8             |  5.94           |  24.94           |  23.67          |  15.77
-    ---------------------------------------------------------------------------------------------------------
-              dp-0.9             |  5.96           |  27.30           |  25.63          |  15.46
-    ---------------------------------------------------------------------------------------------------------
-−
-   (2) Train: train_nosiy
      drop-retention/testcase(WER) | test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1
      ---------------------------------------------------------------------------------------------------------
@@ 第91行： / 第75行： @@
     ---------------------------------------------------------------------------------------------------------
 :** Test with AURORA4 of 7000 (clean + noisy).
 :** Follow the standard DNN training learn-rate to avoid the different learn-rate changing time of various DNN training. Similar performance is obtained.
 :** Find and test unknown noise test-data.(+)
-:** Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5).
+:** Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). Seems small learn-rate get the balance of accuracy and train-time.
 :** Draft the dropout-DNN weight distribution. (++)
 * Rectification
-:* Still NAN error, need to debug.
+:* 1) AURORA 4 -15h
-) AURORA 4 -15h
    (1) Train: train_clean
        learn-rate/testcase(WER)  | test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1
@@ 第131行： / 第113行： @@
      ---------------------------------------------------------------------------------------------------------
 :* Combine drop out and rectifier.
 :* Change the learn-rate in the middle of the training, Modify the train_nnet.sh script(Liu Chao).
@@ 第211行： / 第192行： @@
-* sub word unit language model is ready. on testing.
+* sub word unit language model is ready. Done.
 ====Scoring====

@@ 第243行： / 第243行： @@
 ===Translation===
-* v3.0 demo released
+* v4.0 demo released
-:* still slow
+:* cut the dict and use new segment-tool
-:* re-segment the word using new dictionary.will use the tencent-dic about 11w.
-:* check new data.
 ===QA===

@@ 第215行： / 第215行： @@
 ====RNN LM====
 *rnn
-:* RNNLM=>ALPA
+:* RNNLM=>ALPA make a report
-:* train RNNLM on Chinese data from jietong-data
+:* test RNNLM on Chinese data from jietong-data
 *lstm+rnn
-:* wer:6.2%(4-epoch).need to check the problem.
+:* check the lstm-rnnlm code
 ===Word2Vector===

@@ 第198行： / 第198行： @@
 ====Domain specific LM====
 * domain lm
-:* am:1400h(2.0.b) .result: xiaomi-29.43%,baiduzhidao-43.46%,baiduHi-30.02%, test-set:8ksentence(16k=>8k)
+:* weibo lm with pruning 0 10 10 20 20 testing done. weibo lm with pruning 0 10 8 8 8 under testing. weibo lm without pruning 4/8 done.
-:* need to check the xiaomin-lm method and result.
+:* merger weibo、baiduhi and baiduzhidao lm and test ('''this week''')
 *  new dict.
-:* weibo-data : Tencent-segment and count. get 16k words to segment again.
+:* train lm on baiduhi, baiduzhida with new 150k dict and test ('''this week''')
-:* new toolkit:find method to update the new dict. can get new wordlist from sougou and get word information from baidu.
+:* new toolkit:find method to update the new dict. can get new wordlist from sougou and get word information from baidu.('''two week''')
 ====tag LM====
 * set new test
-:* 1k address from dianxin. prepare to test.
+:* fix the bug
-:* insert the new unknown-address to test set.
+:* record test set and test the unknown address ('''this week''')
-:* record test set 15-sentence/person on dianxin txt.
 ====RNN LM====