Mengyuan Zhao 2015-09-21

From cslt Wiki
Jump to: navigation, search
  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.