Difference between revisions of "Mengyuan Zhao 2015-09-21"

From cslt Wiki
Jump to: navigation, search
(以“#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en dataset. #Do a series of experiments about gradient optimization algorithm on sinovoice & tencent...”为内容创建页面)
 
 
Line 1: Line 1:
#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en dataset.
+
#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en & 1700h+776h cn dataset.
 
#Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.
 
#Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.

Latest revision as of 04:06, 21 September 2015

  1. Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en & 1700h+776h cn dataset.
  2. Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.