Difference between revisions of "140428-Shi Yin"

From cslt Wiki
Jump to: navigation, search
(以内容“=== Accomplished this week === * Decoding on evil92 data set on iteration 1-4. * Completed the whole job about smoothing the results of VAD with DNN. * Tested the resul...”创建新页面)
 
Line 1: Line 1:
 
=== Accomplished this week ===
 
=== Accomplished this week ===
* Decoding on evil92 data set on iteration 1-4.
+
* Found the noisy-training directory and listed the current process.
* Completed the whole job about smoothing the results of VAD with DNN.
+
* Partially got the models by narrow-band noisy-training.
* Tested the results of VAD with DNN and analyzed their performance.  
+
* Perfectly read the code of VAD.  
* Partially completed the job about integrating the code of VAD with DNN into the framework of VAD.
+
* Read the papers about MAP and MLLR.
+
  
 
=== Next Week ===
 
=== Next Week ===
 
* Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD.
 
* Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD.
 
* Decoding on dev93 data set on iteration 1-4 and analyze the results.
 
* Decoding on dev93 data set on iteration 1-4 and analyze the results.
* Try to fix the DNN model by MAP or MLLR.
+
* Decoding on the models of narrow-band noisy-training.
* Find the noisy-training directory and list the current process.
+
* Try to fix the DNN model by MAP or MLLR for far-field ASR.
* Go on completing the job about narrow-band noisy-training.
+

Revision as of 12:52, 5 May 2014

Accomplished this week

  • Found the noisy-training directory and listed the current process.
  • Partially got the models by narrow-band noisy-training.
  • Perfectly read the code of VAD.

Next Week

  • Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD.
  • Decoding on dev93 data set on iteration 1-4 and analyze the results.
  • Decoding on the models of narrow-band noisy-training.
  • Try to fix the DNN model by MAP or MLLR for far-field ASR.