2014-04-18

来自cslt Wiki
2014年4月18日 (五) 02:35Cslt讨论 | 贡献的版本

(差异) ←上一版本 | 最后版本 (差异) | 下一版本→ (差异)
跳转至: 导航搜索

Resoruce Building

  • quota on /nfs/disk this Saturday
  • release management should be started: Zhiyong
  • Blaster 0.1 & vivian 0.0 system release

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
  • Found a paper in 2000 with similar ideas.
  • Try to get a student working on high performance computing to do the optimization

Noise training

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

AMR compression re-training

  • 1700h MPE adaptation done
  • 1700h stream mode adaptation runs into MPE4 done
  • Stream model is better than non-stream wave

GFbank

  • GFBank Sinovoice test on 100h MPE
  • Tencent 100h MPE training done

Multilingual ASR

  • all phone strategy baseline done
  • Testing on Mandarin & English individually

Denoising & Farfield ASR

  • re-Recording done
  • Prepare to construct the baseline

VAD

  • Code ready, migrate to the VAD code framework

Scoring

  • g-score based on MLP is done
  • t-score based on linear regression improves the performance

Word to Vector

  • Dimension of low space varies from 10-100
  • 8-thread word vector generation is 3 times faster than the LDA.

LM development

NN LM

  • Character-based NNLM (6700 chars, 7gram), 500M data training done.
  • Non-boundary char LM is better than boundary char LM
  • Investigate MS RNN LM training


QA

FST-based matching

  • Word-based FST 1-2 seconds with 1600 patterns. Huilan's implementation <1 second. ????
  • Char-FST Implementation is done. Not so effective.


Speech QA

  • Investigate determinization of G embedding