2013-04-26

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.