“2013-04-26”版本间的差异
来自cslt Wiki
| （相同用户的5个中间修订版本未显示） | |||
| 第6行： | 第6行： | ||
===400 hour DNN training=== | ===400 hour DNN training=== | ||
{| class="wikitable" | {| class="wikitable" | ||
| − | !Test Set!! Tencent Baseline!! bMMI!! fMMI !! BN(with fMMI) !! Hybrid | + | !Test Set!! Tencent Baseline!! bMMI!! fMMI !! BN(with fMMI) !! Hybrid (DNN/HMM) |
|- | |- | ||
|1900||8.4 || 7.65 || 7.35||6.57 || 7.27 | |1900||8.4 || 7.65 || 7.35||6.57 || 7.27 | ||
| 第39行： | 第39行： | ||
:LM: 88k LM | :LM: 88k LM | ||
:Test case: general | :Test case: general | ||
| − | : | + | :param=700k |
{|class="wikitable" | {|class="wikitable" | ||
| 第46行： | 第46行： | ||
|PLP(-5,+5) [Eryu] || 47 || 38.4 || 26.5 || 23.8 ||300*1200*1200*1200*1200]*1700 | |PLP(-5,+5) [Eryu] || 47 || 38.4 || 26.5 || 23.8 ||300*1200*1200*1200*1200]*1700 | ||
|- | |- | ||
| − | |PLP+LDA+MLLT(-5,+5)[Jingbo] || 47 || -|| 34 ||300*[1007*1007*1007*1007]*3xxx | + | |PLP+LDA+MLLT(-5,+5)[Jingbo] || 47 || -|| 34 || - ||300*[1007*1007*1007*1007]*3xxx |
|- | |- | ||
|} | |} | ||
| 第52行： | 第52行： | ||
*To be done: | *To be done: | ||
| − | :#CSLT reproduce phone-clustered | + | :#CSLT: reproduce phone-clustered NN (Eryu's results) |
| − | :#CSLT investigate performance of different | + | :#CSLT: investigate performance of different epoches. |
:#Tencent: feature comparison. | :#Tencent: feature comparison. | ||
| − | :#FBank with PLP. With or without LDA. | + | :#Tencent: FBank with PLP. With or without LDA. |
| 第81行： | 第81行： | ||
*Status: | *Status: | ||
:# QA LM training, done. | :# QA LM training, done. | ||
| − | :# PocketSphinx migration done, using PocketSphinx default Chinese model. After migrating to the smart phone, the test shows that the decoding is very slow | + | :# PocketSphinx migration done, using PocketSphinx default Chinese model. After migrating to the smart phone, the test shows that the decoding (with an LM involving 90k words) is very slow (RT=7.0). |
| − | *To | + | *To be done |
| − | :# | + | :# substitute the LM with JSGF grammar involving 1000 words. Finish the initial test. |
:# Need to train a new AM. | :# Need to train a new AM. | ||
2013年4月26日 (五) 07:14的最后版本
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 (DNN/HMM) |
|---|---|---|---|---|---|
| 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 |
- Note
- 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
- To be done:
- 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
- param=700k
| Feature | GMM | GMM-bMMI | DNN | DNN-MMI | DNN structure |
|---|---|---|---|---|---|
| PLP(-5,+5) [Eryu] | 47 | 38.4 | 26.5 | 23.8 | 300*1200*1200*1200*1200]*1700 |
| PLP+LDA+MLLT(-5,+5)[Jingbo] | 47 | - | 34 | - | 300*[1007*1007*1007*1007]*3xxx |
- To be done:
- CSLT: reproduce phone-clustered NN (Eryu's results)
- CSLT: investigate performance of different epoches.
- Tencent: feature comparison.
- Tencent: FBank with PLP. With or without LDA.
GPU & CPU merge
- Investigate the possibility to merge GPU and CPU code.
- Decision: CUDA code merged to CPU.
L-1 sparse initial training
- Initial trial
- L-1=1e-5, starting from 6th iteration, converged with another 3 iterations. The performance is generally worse than the case where l1=0, except one test suite.
- L-1=1e-6, the same results obtained, means le-6 is too small to be effective.
- L-1=1e-4, start from the first iteration. crashed. Need more investigation.
- To be done
- Investigate other L-1 choice, starting from the scratch.
Kaldi/HTK merge
- HTK2Kaldi: hold.
- Kaldi2HTK: done with implementation. A bug fixed. gConst was computed in a wrong way. The current HDecode result is 14.9%; The tencent model is 11%; Kaldi decoder 7%.
- Possibly the SP model issue, due to the complicated structure of silence in Kaldi.
- To be done
- Try other possible SP, e.g., duplicate the silence model, with a jump arck from the start to the end.
- Try borrow SP from the HTK model
Embedded progress
- Status:
- QA LM training, done.
- PocketSphinx migration done, using PocketSphinx default Chinese model. After migrating to the smart phone, the test shows that the decoding (with an LM involving 90k words) is very slow (RT=7.0).
- To be done
- substitute the LM with JSGF grammar involving 1000 words. Finish the initial test.
- Need to train a new AM.
