“Lantian Li 2016-01-11”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
Weekly Summary | Weekly Summary | ||
| − | In this week, lots of miscellaneous things have effect the research progress. | + | In this week, lots of miscellaneous things have effect the research progress [1-4]. |
1. Help Prof.Zheng complete and submit the 'replay detection' patent; | 1. Help Prof.Zheng complete and submit the 'replay detection' patent; | ||
| 第12行： | 第12行： | ||
5. For the max-margin metric learning task, make some additional experiments. | 5. For the max-margin metric learning task, make some additional experiments. | ||
| + | |||
And I find that there is something wrong on the the NIST-SRE05 label (wav.scp, spk2utt, utt2spk), | And I find that there is something wrong on the the NIST-SRE05 label (wav.scp, spk2utt, utt2spk), | ||
| + | |||
and the SRE05 have been re-labelled. | and the SRE05 have been re-labelled. | ||
2016年1月11日 (一) 14:32的版本
Weekly Summary
In this week, lots of miscellaneous things have effect the research progress [1-4].
1. Help Prof.Zheng complete and submit the 'replay detection' patent;
2. Prepare the 973 project report, and attend the meeting in Tianjin.
3. Help Wang Gang on the DNN-based truncated speech detection.
4. Help Prof.Zheng check and submit the two overview paper.
5. For the max-margin metric learning task, make some additional experiments.
And I find that there is something wrong on the the NIST-SRE05 label (wav.scp, spk2utt, utt2spk),
and the SRE05 have been re-labelled.
Next Week
1. Start to work on the task 5.
