“140707 - Lantian Li”版本间的差异
来自cslt Wiki
| 第3行： | 第3行： | ||
1.Make a new database to train the UBM and re-implement the experiment from last week. | 1.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 | + | 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. | it still had effect on the system performance. | ||
2.Using the re-weighted GMM-UBM system to make digital speaker recognition. | 2.Using the re-weighted GMM-UBM system to make digital speaker recognition. | ||
| + | |||
| + | 3.prepare some materials for the "Dynamic Speech Password" patent. | ||
Next Week | Next Week | ||
| − | 1.Go on the task1 | + | 1.Go on the task1, to check the code of the modified UBM training tool. |
| + | |||
| + | 2.Finish task2. | ||
| + | |||
| + | 3.Help D-ear company to copy NIST databset. | ||
2014年7月7日 (一) 14:04的版本
Weekly Summary
1.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 tool,accoring to the HTK,which could avoid the code-empty problem,
it still had effect on the system performance.
2.Using the re-weighted GMM-UBM system to make digital speaker recognition.
3.prepare some materials for the "Dynamic Speech Password" patent.
Next Week
1.Go on the task1, to check the code of the modified UBM training tool.
2.Finish task2.
3.Help D-ear company to copy NIST databset.
