“140623 - Jun Wang”版本间的差异
来自cslt Wiki
（以内容“weekly summary 1\extractor bottleneck features, the dnn structure is 220:1024:1024:40:1024:1024:6950 2\test bottleneck features in ivector framework, the results are ...”创建新页面） |
（没有差异）
|
2014年6月25日 (三) 09:58的最后版本
weekly summary
1\extractor bottleneck features, the dnn structure is 220:1024:1024:40:1024:1024:6950
2\test bottleneck features in ivector framework, the results are posted on the CVSS
next week
1\use pretraining 5:5:5:5:5:1000 for dnn training and re-extractor the bottleneck features.
2\also test in the ivector framework
