140707 - Lantian Li - 版本历史

2014年7月7日 (一) 14:04 Lilt

2014-07-07T14:04:40Z

2014年7月7日 (一) 14:04 Lilt

2014-07-07T14:04:22Z

2014年7月7日 (一) 14:00 Lilt

2014-07-07T14:00:08Z

Lilt：以内容“Weekly Summary 1.Two groups of experiments were made under the condition of different window_size and shift_size. And found that after unified shift_size and fixed th...”创建新页面

2014-07-07T13:49:17Z

以内容“Weekly Summary 1.Two groups of experiments were made under the condition of different window_size and shift_size. And found that after unified shift_size and fixed th...”创建新页面

新页面

Weekly Summary

1.Two groups of experiments were made under the condition of different window_size and shift_size.

And found that after unified shift_size and fixed the number of frames,female is more sensitive than male.

Male presents a certain stability, while female in 20-10ms to 24-12ms exites an obvious turning point and has strong sensitivity to window_size and

shift_size.

2.Using the re-weighted GMM-UBM system to

Next Week

1.Go on the task1 and task2.

@@ 第9行： / 第9行： @@
 .Using the re-weighted GMM-UBM system to make digital speaker recognition.
-.prepare some materials for the "Dynamic Speech Password" patent.
+.Prepare some materials for the "Dynamic Speech Password" patent.
 Next Week

@@ 第3行： / 第3行： @@
 .Make a new database to train the UBM and re-implement the experiment from last week.
-Found that although we had modified the UBM training tools,accoring to the HTK,which could avoid the code-empty problem,
+Found that although we had modified the UBM training tool,accoring to the HTK,which could avoid the code-empty problem,
 it still had effect on the system performance.
 .Using the re-weighted GMM-UBM system to make digital speaker recognition.
 Next Week
-.Go on the task1 and task2.
+.Go on the task1, to check the code of the modified UBM training tool.