Sinovoice-2016-5-12

Data

• 16K LingYun

• 2000h data ready
• 4300h real-env data to label

• YueYu

• Total 250h(190h-YueYu + 60h-English)
• Add 60h YueYu
• CER: 75%->76%

• WeiYu

• 50h for training
• 120h labeled ready

• PingAn

• 100h User data done

Deletion Error Promblem

• Add one noise phone to alleviate the silence over-training
• Omit sil accuracy in discriminative training
• H smoothing of XEnt and MPE
• Add one silence arc from start-state to end-state

Big-Model Training

8k=

Model

• Add noise phone

• 1300.mdl done

• CNN + TDNN

• 280/900 mdl
• Need about 12 days Xent

Project

• PingAn

• Add noise phone to phone-list

PingAnAll:
 ==================================================================================
 |         AM / error         | tot_err |   ins   |   del   |   sub   |   wer   |
 ----------------------------------------------------------------------------------
 | tdnn 7-1024 xEnt 2500.mdl  |  3626   |   619   |   773   |   2234  |  16.60  |
 ----------------------------------------------------------------------------------
 | spn 7-1024 xEnt 1300.mdl   |  3746   |   702   |   763   |   2281  |  16.xx  |
 ==================================================================================

PingAnUser:
 ==================================================================================
 |         AM / error         | tot_err |   ins   |   del   |   sub   |   wer   |
 ----------------------------------------------------------------------------------
 | tdnn 7-1024 xEnt 2500.mdl  |   549   |   158   |    75   |   316   |  35.91  |
 ----------------------------------------------------------------------------------
 | spn 7-1024 xEnt 1300.mdl   |   571   |   151   |    97   |   323   |  35.xx  |
 ==================================================================================

• LiaoNingYiDong

======================================================================

 |         AM / error         | tot_err |   ins   |   del   |   sub   |   wer   |
 ----------------------------------------------------------------------------------
 | tdnn 7-1024 xEnt 2500.mdl  |   5873  |   879   |   1364  |   3630  |  21.72  |
 ----------------------------------------------------------------------------------
 | spn 7-1024 xEnt 300.mdl    |   6257  |   977   |   1348  |   3923  |  23.14  |
 ==================================================================================

Embedding

• The size of nnet1 AM is 6.4M (3M after decomposition). So we need to control AM size within 10M.
• 5*576-2400 TDNN model training done. AM size is about 17M
• 5*500-2400 TDNN model on training.
• MPE training 2/4 part

• test8000:wer16, test10000:wer30

Character LM

• Except Sogou-2T, 9-gram has been done.
• Add word boundary tag to Character-LM trainig done

• 9-gram
• Except Weibo & Sogou-2T
• 1e-7(13M) wer17.91 compared with 1e-7(no-boundary,71M) 13.4
• 1e-8(54M) wer17.54

• Prepare specific domain vocabulary

• Dianxin/Baoxian/Dianli

• DT lm training

• ReFr

• Merge Character-LM & word-LM

• Union
• Compose, success.

• 2-step decoding: first, character-based LM. Then, word-based LM.

SiaSong Robot

• Beam-forming algorithm test
• NN-model based beam-forming

Project

• Pingan & Yueyu Deletion error too more

• TDNN deletion error rate > DNN deletion error rate
• TDNN Silence scale is too sensitive for different test cases.

SID

Digit

• Engine Package