Difference between revisions of "2013-04-26"

From cslt Wiki
Jump to: navigation, search
Line 1: Line 1:
 
==Data sharing==
 
==Data sharing==
  
* AM/lexicon/LM are shared.
 
 
* LM count files are still in transfering.  
 
* LM count files are still in transfering.  
  
Line 28: Line 27:
  
 
*Tencent baseline is with 700h online data+ 700h 863 data, HLDA+MPE, 88k lexicon
 
*Tencent baseline is with 700h online data+ 700h 863 data, HLDA+MPE, 88k lexicon
*Our results are with 400 hour AM, 88k LM. ML+bMMI
+
*Our results are with 400 hour AM, 88k LM. ML+bMMI.
 +
*The CSLT structure: 300*[1200*1200*1200*40*1200]*4850.
 +
 
 +
* compare with the traditional structure 300*[1200*1200*1200*1200*1200]*4850.
 +
 
  
 
===Tencent test result===
 
===Tencent test result===

Revision as of 06:02, 26 April 2013

Data sharing

  • LM count files are still in transfering.

DNN progress

400 hour DNN training

Test Set Tencent Baseline bMMI fMMI BN(with fMMI) Hybrid
1900 8.4 7.65 7.35 6.57 7.27
2044 22.4 24.44 24.03 21.77 20.24
online1 35.6 34.66 34.33 31.44 30.53
online2 29.6 27.23 26.80 24.10 23.89
map 24.5 27.54 27.69 23.79 22.46
notepad 16 19.81 21.75 15.81 12.74
general 36 38.52 38.90 33.61 31.55
speedup 26.8 27.88 26.81 22.82 22.00
  • Tencent baseline is with 700h online data+ 700h 863 data, HLDA+MPE, 88k lexicon
  • Our results are with 400 hour AM, 88k LM. ML+bMMI.
  • The CSLT structure: 300*[1200*1200*1200*40*1200]*4850.
  • compare with the traditional structure 300*[1200*1200*1200*1200*1200]*4850.


Tencent test result

AM: 70h training data(2 day, 15 machines, 10 threads)
LM: 88k LM
Test case: general
Feature GMM-bMMI DNN DNN-MMI
PLP(-5,+5) 38.4 26.5 23.8
PLP+LDA+MLLT(-5,+5) 38.4 28.7


GPU & CPU merge

Invesigate the possibility to merge GPU and CPU code. GPU computing code merged to CPU.

L-1 sparse initial training

Start to investigating.

Kaldi/HTK merge

  • HTK2Kaldi: hold.
  • Kaldi2HTK: done with implementation. Performance improved.

Embedded progress

  • PocketSphinx migration done. Very slow.
  • QA LM training, done.