2014年8月1日 (五) 01:53 Cslt

2014-08-01T01:53:02Z

Cslt：以内容“==Resoruce Building== == Leftover questions== * Investigating LOUDS FST. * CLG embedded decoder plus online compiler. * DNN-GMM co-training * NN LM == AM developmen...”创建新页面

2014-08-01T01:52:34Z

以内容“==Resoruce Building== == Leftover questions== * Investigating LOUDS FST. * CLG embedded decoder plus online compiler. * DNN-GMM co-training * NN LM == AM developmen...”创建新页面

新页面

==Resoruce Building==

== Leftover questions==

* Investigating LOUDS FST.
* CLG embedded decoder plus online compiler.
* DNN-GMM co-training
* NN LM

== AM development ==

=== Sparse DNN ===
* WJS sparse DNN shows a slightly better than non-sparse cases when the network is in a large scale
* Pre-training does work for DNN training (for both 4/5/6 layers)

===Noise training===
:* Journal paper writing on going

===Multilingual ASR===

* Native English speaker + Chinglish speaker obtained better performance.

==Drop out & convolutional network==

* Change learning to 0.001, the training process can be started.
* Frame Accuracy goes to : (with/without drop probability normalization)

===Denoising & Farfield ASR===

* By tuning parameters of late-response lag & response time, obtained performance improvement with Lasso.

Simulation results: Baseline:
--------------------------------------------------------------------------
model/test | far_evl92 | near_evl92
--------------------------------------------------------------------------
clean_ce | 59.38 | 19.25
mpe_clean_ce | 40.46 | 12.94
--------------------------------------------------------------------------

Lasso with optimal parameters(lambda=0.05, delta=5, N=10)
--------------------------------------------------------------------------
model/test | far_evl92 | near_evl92
--------------------------------------------------------------------------
clean_ce | 54.63 | 15.75
--------------------------------------------------------------------------
mpe_clean_ce | 36.58 | 11.64
--------------------------------------------------------------------------

Real data results:
--------------------------------------------------------------------------
model/test | far_evl92 | near_evl92
--------------------------------------------------------------------------
clean_ce | 94.86 | 63.48
--------------------------------------------------------------------------
mpe_clean_ce | 92.29 | 58.37
--------------------------------------------------------------------------
dereverberated recording :

--------------------------------------------------------------------------
model/test | far_evl92 | near_evl92
--------------------------------------------------------------------------
clean_ce | 94.91 | 61.03
--------------------------------------------------------------------------
mpe_clean_ce | 91.28 | 54.16
--------------------------------------------------------------------------

* Adaptation under running

===VAD===

* Waiting for testing results

===Scoring===

* Refine the acoustic model with AMIDA database. problem solved by involving both wsj and AMIDA.

===Confidence===

* Be familiar with Kaldi
* Need to extract lattice and DNN features

===Embedded decoder===

* Chatting LM released (80k)
* Train two smaller network: 500x4+600, 400x4+500: on going
* Need to upload the new client code onto git (+)
* Build a new graph with MPE3 am and chatting LM.

==LM development==

===Domain specific LM===

h2. Domain specific LM construction

h3. TAG LM

* TAG obtained better performance

h3. Chatting LM

* First version released (80k lexicon)
* Prepare 2nd released (120k lexicon)
* Test on Xiaotang long

==Word2Vector==

===W2V based doc classification===

* Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.

==Speaker ID==

* Full-data SRE trial goes into the final stage
* results will be ready soon

==Translation==
* collecting more data (Xinhua parallel text, bible, name entity) for the second version
* check possible parameters to control phrase pair lexicon

@@ 第33行： / 第33行： @@
 * By tuning parameters of late-response lag & response time, obtained performance improvement with Lasso.
 Simulation results: Baseline:
 --------------------------------------------------------------------------
@@ 第68行： / 第69行： @@
 --------------------------------------------------------------------------
 * Adaptation under running

2014-08-01 - 版本历史

2014年8月1日 (五) 01:53 Cslt

Cslt：以内容“==Resoruce Building== == Leftover questions== * Investigating LOUDS FST. * CLG embedded decoder plus online compiler. * DNN-GMM co-training * NN LM == AM developmen...”创建新页面