2013-04-19

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. 

   BN-fmmi outperforms the MFCC-fmmi baseline: 13.5%
   BN-fmmi vs DNN-HMM hybrid: xx%

(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?