Xiangyu Zeng 2016-05-02

Last week:

1.repeat experiments on the wsj dataset, but met a problem that KALDI_ASSERT: at nnet-train-frmshuff-adammax-last:Eval:nnet-loss.cc:73, failed: KALDI_ISFINITE(net_out.Sum()). I guess that is caused by copied data, and the net train the same utterance continuous.

2.revised the paper of online learning, and change the dataset settings.

Next week:

1.fix the bug of 1, and add NG experiments into paper.