140623 - Jun Wang

From cslt Wiki
Jump to: navigation, search

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