2014-03-28

Resoruce Building

• Current text resource has been re-arranged and listed

Leftover questions

• Asymmetric window: Great improvement on training set(WER 34% to 24%), however the improvement is lost on test. Overfitting?
• Multi GPU training: Error encountered
• Multilanguage training
• Investigating LOUDS FST.
• CLG embedded decoder plus online compiler.
• DNN-GMM co-training

AM development

Sparse DNN

• GA-based block sparsity

• 88% element-sparsity: 25.09
• 80% block-sparsity: 25.5

Noise training

• More experiments with no-noise
• More experiments with additional noise types

AMR compression re-training

• 1700h MPE adaptation

• iter1:

amr: %WER 13.40 [ 6398 / 47753, 252 ins, 829 del, 5317 sub ] wav: %WER 11.19 [ 5343 / 47753, 178 ins, 710 del, 4455 sub ]

• iter2:

amr: %WER 13.31 [ 6358 / 47753, 255 ins, 798 del, 5305 sub ] wav: %WER 11.33 [ 5409 / 47753, 180 ins, 732 del, 4497 sub ]

GFbank

• gfbank on Tentent 100h

Word to Vector

• LDA baseline (sogou 1700*9 training set)

• Memory usage more than 20G

• Word-vector classification on going

• Model based on category wordvector clustering

LM development

NN LM

• Character-based NNLM (6700 chars, 7gram), 500M data training done.

• boundary-involved char NNLM training done

• Investigate MS RNN LM training

Pronunciation scoring

• 8k model delivered
• MLP-based scoring completed

QA

FST-based matching

• Char FST
• Prepare FST-based QA patent

Speech QA

• Class LM QA

• Now find that with smaller weight to the class FST, better performance is obtained
• Now it is very difficult to retrieve the words that can not be found by the original FST
• Test negative weights