Zhiyuan Tang 2015-03-23

来自cslt Wiki
2015年3月23日 (一) 13:36Tangzy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:

got a better understanding of ASR with some papers;

did some easy analysis about the weights of DNN already learned from Kaldi to see if some intersting things could be found and more regularization could be added to train a better DNN;

the CONTEXT into DNN may be not enough, as the central frame is not highlighted and its neighbors should not share the same importance. Analysis of the first-layer weights may give some insight to improve the CONTEXT.


This week:

do more analysis about the learned weights;

improve the CONTEXT if possible, at least give it some small changes and contrast its performance with previous results.