“2018-12-12”版本间的差异
来自cslt Wiki
(4位用户的5个中间修订版本未显示) | |||
第10行: | 第10行: | ||
|Yibo Liu | |Yibo Liu | ||
|| | || | ||
− | * | + | * Read how code of poem_acl2017 different from code of NMT. |
+ | * Checked book reference. | ||
|| | || | ||
− | * | + | * Finish modifying code of poem_acl2017 on memory module. |
|| | || | ||
* | * | ||
第23行: | 第24行: | ||
|Xiuqi Jiang | |Xiuqi Jiang | ||
|| | || | ||
− | * Learned TensorFlow documents about seq2seq model and made adjustments on vivi | + | * Learned TensorFlow documents about seq2seq model and made adjustments on vivi's params |
* Had some problems on encoder-memory and decoder-memory, and was trying to figure out the difference | * Had some problems on encoder-memory and decoder-memory, and was trying to figure out the difference | ||
|| | || | ||
第52行: | 第53行: | ||
|Zhaodi Qi | |Zhaodi Qi | ||
|| | || | ||
− | * | + | * attend an academic conference |
|| | || | ||
− | * | + | *keep on research of DID |
|| | || | ||
− | * | + | * |
|- | |- | ||
第65行: | 第66行: | ||
|Jiawei Yu | |Jiawei Yu | ||
|| | || | ||
− | * | + | * Read attention recipe on kaldi and try to establish baseline use thch30 |
+ | * read the "PHONETIC-ATTENTION SCORING FOR DEEP SPEAKER FEATURES IN SPEAKER VERIFICATION" and “GAUSSIAN-CONSTRAINED TRAINING FOR SPEAKER VERIFICATION” | ||
|| | || | ||
− | * | + | * finish attention baseline |
|| | || | ||
* | * | ||
第76行: | 第78行: | ||
|Yunqi Cai | |Yunqi Cai | ||
|| | || | ||
− | * | + | * Read "Introduction to modern machine learning technology" |
+ | *Check the ref. | ||
+ | *do some preparation about how to use the kaldi | ||
|| | || | ||
− | * | + | * run the demo of thchs30 |
|| | || | ||
* | * |
2018年12月12日 (三) 03:50的最后版本
People | Last Week | This Week | Task Tracking (DeadLine) |
---|---|---|---|
Yibo Liu |
|
|
|
Xiuqi Jiang |
|
|
|
Jiayao Wu |
|
|
|
Zhaodi Qi |
|
|
|
Jiawei Yu |
|
|
|
Yunqi Cai |
|
|
|
Dan He |
|
|
|
Yang Zhang |
|
|
|