“2013-04-19”版本间的差异

2013年4月19日 (五) 06:04的版本

1. Data sharing

(1) AM/lexicon/LM are shared.

(2) LM count files are still in transfering.

2. DNN progress

(1) 400 hour BN model.

(2) Tencent test result: 70h training data(2 day, 15 machines, 10 threads), 88k LM, general test case:

gmmi-bmmi: 38.7% dnn-1: 28% 11 frame window, phone-based tree dnn-2: 34% 9 frame window, state-based tree

(2) GPU & CPU merge. Invesigate the possibility to merge GPU and CPU code. Try to find out an easier way. (1 week)

3.Kaldi/HTK merge

(1) HTK2Kaldi: the tool with Kaldi does not work.
(2) Kaldi2HTK: done with implementation. Testing?

4. Embedded progress

(1). Some large performance (speed) degradation with the embedded platform(1/60).

(2). Planning for sparse DNN.

(3). QA LM training, Mengyuan?

@@ 第7行： / 第7行： @@
 . DNN progress
-  (1) 400 hour BN model. Tencent test result?
+  (1) 400 hour BN model.
- (2) GPU and CPU style comparision: still on progress. Working on data checking. SGE is still problematic (Chao can help). Hopefully done in 1 or two weeks.
+ (2) Tencent test result: 70h training data(2 day, 15 machines, 10 threads), 88k LM, general test case:
+gmmi-bmmi: 38.7%
+dnn-1: 28%  11 frame window,  phone-based tree
+dnn-2: 34%  9  frame window,  state-based tree
+ (2) GPU & CPU merge. Invesigate the possibility to merge GPU and CPU code. Try to find out an easier way. (1 week)
 .Kaldi/HTK merge