Cslt：/* Embedded development */

2014-01-20T12:35:52Z

‎Embedded development

Cslt：以内容“== AM development == === Sparse DNN === * Optimal Brain Damage(OBD). # Online OBD held. # OBD + L1 norm start to investigation. * Efficient computing # Conducti...”创建新页面

2014-01-17T01:49:02Z

以内容“== AM development == === Sparse DNN === * Optimal Brain Damage(OBD). # Online OBD held. # OBD + L1 norm start to investigation. * Efficient computing # Conducti...”创建新页面

新页面

== AM development ==

=== Sparse DNN ===

* Optimal Brain Damage(OBD).

# Online OBD held.
# OBD + L1 norm start to investigation.

* Efficient computing

# Conducting rearrangement the matrix structure and compose zero blocks by some smart approaches, leading to better computing speed.

=== Efficient DNN training ===

# Asymmetric window: Great improvement on training set(WER 34% to 24%), however the improvement is lost on test. Overfitting?
# 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==

===NN LM===

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

==Embedded development==

* Waiting for CLG engine to boost integration
* 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

@@ 第41行： / 第41行： @@
 ==Embedded development==
-* Waiting for CLG engine to boost integration
+* CLG embedded decoder is almost done. The graph compilation is highly fast.
 * Work on layer-by-layer DNN training, initial model is incorrect.

2014-01-17 - 版本历史

Cslt：/* Embedded development */

Cslt：以内容“== AM development == === Sparse DNN === * Optimal Brain Damage(OBD). # Online OBD held. # OBD + L1 norm start to investigation. * Efficient computing # Conducti...”创建新页面