“2014-11-25”版本间的差异

2014年11月24日 (一) 11:42的版本

Speech Processing

AM development

Environment

• Already buy 3 760GPU
• grid-9 760GPU crashed again;
• Change 760gpu card of grid-12 and grid-14

Sparse DNN

• Performance improvement found when pruned slightly
• need retraining for unpruned one; training loss
• details at http://liuc.cslt.org/pages/sparse.html

RNN AM

• Initial nnet seems not very well, need to be pre-trained or test lower learn-rate.
• For AURORA 4 1h/epoch, model train done.
• Using AURORA 4 short-sentence with a smaller number of targets.(+)
• Adjusting the learning rate.(+)
• Trying toolkit of Microsoft.(+)
• details at http://liuc.cslt.org/pages/rnn.html

A new nnet training scheduler

• Initial code done. No better than original one considering of taking much more iterations.
• details at http://liuc.cslt.org/pages/nnet-sched.html

Drop out & Rectification & convolutive network

• Drop out

• AURORA4 dataset

• Use different proportion of noise data to investigate the effect of xEnt and mpe and dropout
  • Problem 1) The effect of dropout in different noise proportion;

          2) The effect of MPE in different noise proportion;
          3) The effect of MPE+dropout in different noise proportion.

• • http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=261

• • Find and test unknown noise test-data.(++)
  • 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.
  • Debug the low cv frame-accuracy

• MaxOut

• 6min/epoch

1) AURORA4 -15h
   NOTE: gs==groupsize

• pretraining based maxout
  • Select units in Groupsize interval, but need low learn-rate
  • Force accept the first iteration. Jump out from the local-minimum

• P-norm

   ---------------------------------------------------------------------------------------------------------
        model/testcase(WER)    | test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1 
   ---------------------------------------------------------------------------------------------------------
       nnet_std-baseline       |  6.04           |  29.91           |  27.76          |  16.37
   ---------------------------------------------------------------------------------------------------------
       lr0.008-1e-7_gs6_p2     |  6.17           |  27.51           |  24.98          |  15.40 
   ---------------------------------------------------------------------------------------------------------
       lr0.008-1e-7_gs10_p2    |  6.40           |  28.18           |  26.60          |  15.82 
   ---------------------------------------------------------------------------------------------------------
       lr0.008-1e-7_gs10_p3    |  6.45           |  28.73           |  30.01          |  20.24 
   ---------------------------------------------------------------------------------------------------------
       lr0.04-4e-3_gs6_p2      |  6.47           |  27.42           |  27.48          |  17.35 
   ---------------------------------------------------------------------------------------------------------

• Convolutive network (+)

• AURORA 4

:** 1)
-----------------------------------------------------------------------------------------------------------------------
                 |  wer | hid-layers | hid-dim | delta-order | splice | lda-dim | learn-rate	| pooling | TBA
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_baseline| 6.70 |     4      | 1200	|      0      |    4   |   198   |   0.008	|   3     |patch-dim1 7 
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_1000_3  | 6.61 |     4      | 1000	|      0      |    4   |   198   |   0.008	|   3     |patch-dim1 7 
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_1400_3  | 6.61 |     4      | 1400	|      0      |    4   |   198   |   0.008	|   3     |patch-dim1 7 
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_1200_4  | 6.91 |     4      | 1200	|      0      |    4   |   198   |   0.008	|   4     |patch-dim1 6 
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_1200_2  | -    |     4      | 1200	|      0      |    4   |   198   |   0.008	|   2     |patch-dim1 8 
-----------------------------------------------------------------------------------------------------------------------
 cnn_std_1200_3  | 6.66 |     5      | 1200	|      0      |    4   |   198   |   0.008	|   3     |patch-dim1 7 
-----------------------------------------------------------------------------------------------------------------------
:** 2)
 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
                                       | %WER          | Dnnhiddenlayers       | hid-dim       | pooling       | CNN_unit      |cnn_init_opts
 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 cnn_nonlda_std			| 5.73		| 4			| 1200    	| 3 		|  		|"--patch-dim1 8" input_dim ~ patch-dim1
 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 cnn_nonlda_cnnunit_384		| 5.85		| 4			| 1200    	| 3		| 384		|"--patch-dim1 8 --num-filters2 384"	   
 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 cnn_nonlda_cnnunit_220		| ----------    | 4			| 1200    	| 3		| 220		|"--patch-dim1 8 --num-filters2 220"	   
 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------

MSE

(1) AURORA4 (train_clean)
   drop-retention/testcase(WER) | test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1 
   ---------------------------------------------------------------------------------------------------------
          std-baseline_xent     |  6.04           |  29.91           |  27.76          |  16.37
   ---------------------------------------------------------------------------------------------------------
          std-baseline_mse      |  6.05           |  31.30           |  30.03          |  15.77
   ---------------------------------------------------------------------------------------------------------

DAE(Deep Atuo-Encode)

 (1) train_clean
   drop-retention/testcase(WER)| test_clean_wv1  | test_airport_wv1 | test_babble_wv1 | test_car_wv1 
  ---------------------------------------------------------------------------------------------------------
      std-xEnt-sigmoid-baseline| 6.04            |    29.91         |   27.76         | 16.37
  ---------------------------------------------------------------------------------------------------------
      std+dae_cmvn_noFT_2-1200 | 7.10            |    15.33         |   16.58         | 9.23
  ---------------------------------------------------------------------------------------------------------
   std+dae_cmvn_splice5_2-100  | 8.19            |    15.21         |   15.25         | 9.31
  ---------------------------------------------------------------------------------------------------------

Denoising & Farfield ASR

• ICASSP paper submitted.
• HOLD

VAD

• Frame energy feature extraction, done
• Harmonics and Teager energy features being investigation (+)
• Previous results to be organized for a paper
• MPE model VAD test

Speech rate training

• Data ready on tencent set; some errors on speech rate dependent model
• Retrain new model(+)

Scoring

• Timber Comparison done.
• harmonics based timber comparison: frequency based feature is better
• GMM based timber comparison is done. Similar to speaker recognition
• TODO: Code checkin and technique report

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 ~ 4% (GMM-based system)--Text independent
• EER ~ 6%(1s) / 0.5%(5s) (GMM-based system)--Text dependent
• test different number of components; fast i-vector computing

Language ID

• GMM-based language is ready.
• Delivered to Jietong
• Prepare the test-case

Voice Conversion

• Yiye is reading materials

Text Processing

LM development

Domain specific LM

• domain lm(need to discuss with xiaoxi)

• embedded language model(this week)
• train some more LMs with Zhenlong (dianzishu sogou bbs chosen)("need result").
• keep on training sogou2T lm(14/16 on 3rd iteration).(this week)

• new dict.

• handover of this work to hanzhenglong, give a simple docuemnt(this week)

tag LM

• different weight 2014-Nov-23,Monday

• conclusion:

 1. compare experiment 3  with experiment 5:
   same jsgf file, but the  tag number in corpus if different, we can find that when add 
 more tag to corpus, the optimal weight is larger.
 2. compare experiment 3 with experiment 6:
  same tag number in corpus, but different jsgf size, we can find that different jsgf size have the 
 same optimal weight.

• need to do

• tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (this week)
• make a summary about tag-lm and journal paper(wxx and yuanb)(two weeks).

RNN LM

• rnn

• test wer RNNLM on Chinese data from jietong-data(this week)
• check the rnnlm code about how to Initialize and update learning rate.
• generate the ngram model from rnnlm and test the ppl with different size txt.(this week)

• lstm+rnn

• check the lstm-rnnlm code about how to Initialize and update learning rate.

Word2Vector

W2V based doc classification

• Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.(hold)
• Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation

Knowledge vector

• Knowledge vector started

• begin to code

Character to wordr

• Character to word conversion(hold)

• prepare the task: word similarity
• prepare the dict.

Translation

• v5.0 demo released

• cut the dict and use new segment-tool

QA

deatil:[1]

Spell mistake

• retrain the ngram model(caoli)

improve fuzzy match

• add Synonyms similarity using MERT-4 method(hold)

improve lucene search

• using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.(liurong this month)

Multi-Scene Recognition

• handover to duxk(this week)

XiaoI framework

• give a report about xiaoI framework
• new inter will install SEMPRE

patent

• GA-method improve the QA(this week)