Zhiyuan Tang 2016-04-18

来自cslt Wiki
2016年4月18日 (一) 00:38Tangzy讨论 | 贡献的版本

(差异) ←上一版本 | 最后版本 (差异) | 下一版本→ (差异)
跳转至: 导航搜索


Last week:

1. enhancing the joint model with SWBD focusing on speech recognition, shows improvement[1];

2. problem remains that when the WSJ was reduced to be 8k, the advantage of joint training disappeared.


This week:

1. find the reason why joint training failed on 8k WSJ;

2. following ICASSP 16.