Mengyuan Zhao 2016-01-25

来自cslt Wiki
跳转至： 导航、 搜索
  • Do some experiment on "chain" model, and got some conclusion:
  1. "chain" model is not sensitive with the number of output layer (pdf_num);
  2. post layer need more context than prior layer
  • Start 11000h "chain" model training for sinovoice.
取自“http://index.cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2016-01-25&oldid=18793”