“Zhiyuan Tang”版本间的差异
来自cslt Wiki
| 第11行： | 第11行： | ||
1. transfer learning(dark knowledge) for nnet3; | 1. transfer learning(dark knowledge) for nnet3; | ||
| − | 2. joint training for speech & speaker recognition(ASSR) . | + | 2. joint training for speech & speaker recognition(ASSR); |
| + | |||
| + | 3. kaldi book: cooperate writing preperation, materials collection. | ||
2016年2月22日 (一) 00:39的版本
Last week:
1. With Mengyuan, conducted experiments for small model with big data, initial results here;
2. got the conlusion that mpe improves chain, results here.
This week:
1. transfer learning(dark knowledge) for nnet3;
2. joint training for speech & speaker recognition(ASSR);
3. kaldi book: cooperate writing preperation, materials collection.
