“2013-04-26”版本间的差异
来自cslt Wiki
第29行: | 第29行: | ||
*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. | *The CSLT structure: 300*[1200*1200*1200*40*1200]*4850. | ||
− | + | *The CSLT feature: MFCC+delta MFCC | |
* compare with the traditional structure 300*[1200*1200*1200*1200*1200]*4850. | * compare with the traditional structure 300*[1200*1200*1200*1200*1200]*4850. | ||
− | |||
===Tencent test result=== | ===Tencent test result=== | ||
− | : AM: 70h training data | + | : AM: 70h training data |
: LM: 88k LM | : LM: 88k LM | ||
: Test case: general | : Test case: general | ||
{|class="wikitable" | {|class="wikitable" | ||
− | !Feature !! GMM-bMMI !! DNN !! DNN-MMI | + | !Feature !! GMM !!GMM-bMMI !! DNN !! DNN-MMI |
|- | |- | ||
− | |PLP(-5,+5) || 38.4 || 26.5 || 23.8 | + | |PLP(-5,+5) [Eryu] || 47 || 38.4 || 26.5 || 23.8 |
|- | |- | ||
− | |PLP+LDA+MLLT(-5,+5) | + | |PLP+LDA+MLLT(-5,+5)[Jingbo] || 47 || - || 34 |
|- | |- | ||
|} | |} | ||
+ | |||
+ | * Tencent NN structure: | ||
+ | :300*[1200*1200*1200*1200]*1700, #param=700k | ||
+ | :300*[1007*1007*1007*1007]*3xxx #param=700k | ||
+ | |||
+ | :*CSLT reproduce phone-clustered based NN | ||
+ | :*CSLT investigate performance of different epochs. | ||
===GPU & CPU merge=== | ===GPU & CPU merge=== | ||
− | : | + | : Investigate the possibility to merge GPU and CPU code. |
+ | : CUDA code merged to CPU. | ||
===L-1 sparse initial training=== | ===L-1 sparse initial training=== |
2013年4月26日 (五) 06:20的版本
目录
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.
- The CSLT feature: MFCC+delta MFCC
- compare with the traditional structure 300*[1200*1200*1200*1200*1200]*4850.
Tencent test result
- AM: 70h training data
- LM: 88k LM
- Test case: general
Feature | GMM | GMM-bMMI | DNN | DNN-MMI |
---|---|---|---|---|
PLP(-5,+5) [Eryu] | 47 | 38.4 | 26.5 | 23.8 |
PLP+LDA+MLLT(-5,+5)[Jingbo] | 47 | - | 34 |
- Tencent NN structure:
- 300*[1200*1200*1200*1200]*1700, #param=700k
- 300*[1007*1007*1007*1007]*3xxx #param=700k
- CSLT reproduce phone-clustered based NN
- CSLT investigate performance of different epochs.
GPU & CPU merge
- Investigate the possibility to merge GPU and CPU code.
- CUDA 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.