From cslt Wiki
Jump to: navigation, search

AM development

Sparse DNN

  • Optimal Brain Damage(OBD).
  1. Online OBD held.
  2. OBD + L1 norm start to investigation.
  • Efficient computing
  1. Conducting rearrangement the matrix structure and compose zero blocks by some smart approaches, leading to better computing speed.

Efficient DNN training

  1. Asymmetric window: Great improvement on training set(WER 34% to 24%), however the improvement is lost on test. Overfitting?
  2. Fbank feature used to train GMM+DNN, leads to very high training Acc, but reduces accuracy on test.

Optimal phoneset

  • Ch/En training with concatenated phone set is completed.
  • Initial test seems reasonable on Chinese. A bit worse than the original test
  • Need to compare the two systems both on Fbank
  • Need to extend the state number

Engine optimization

  • Investigating LOUDS FST. On progress.

LM development


  • Training character-based NN LM, 12134 Chinese chars
  • Prepare data for training word2vector on Gigawords CHS 4.0

Embedded development

  • CLG embedded decoder is almost done. The graph compilation is highly fast.
  • Work on layer-by-layer DNN training, initial model is incorrect.

Speech QA

  • Use N-best to expand match in QA. Better performance were obtained.
  • 1-best matches 96/121
  • 10-best matches 102/121
  • Use N-best to recover errors in entity check.
  • Design a non-entity pattern to discover the possible place of an entity
  • By this position range, search entities within the N-best result
  • Use Pinyin to recover errors in entity check. Future work.
  • Design a non-entity pattern to discover the possible place of an entity (as above)
  • Match the Pinying strings of all the entities, and then match the pinyin strings with the entity pinyin
  • Keep the most matched entity based on Pinyin with a threshold
  • A bit worse then the original test.
  • A possible problem is that the LM is over-strong, thus lead to unmatched Pinyin string in acoustic space
  • Liu rong will provide a weak LM to support the research.
  • Investigate some errors in entity-based LM.
  • Still some errors exist
  • Running entity-base LM with a small entity list