“140428-Shi Yin”版本间的差异
来自cslt Wiki
(以内容“=== Accomplished this week === * Decoding on evil92 data set on iteration 1-4. * Completed the whole job about smoothing the results of VAD with DNN. * Tested the resul...”创建新页面) |
|||
第1行: | 第1行: | ||
=== Accomplished this week === | === Accomplished this week === | ||
− | * | + | * Found the noisy-training directory and listed the current process. |
− | + | * Partially got the models by narrow-band noisy-training. | |
− | * | + | * Perfectly read the code of VAD. |
− | * | + | |
− | + | ||
=== Next Week === | === Next Week === | ||
* Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD. | * Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD. | ||
* Decoding on dev93 data set on iteration 1-4 and analyze the results. | * Decoding on dev93 data set on iteration 1-4 and analyze the results. | ||
− | * Try to fix the DNN model by MAP or MLLR | + | * Decoding on the models of narrow-band noisy-training. |
− | + | * Try to fix the DNN model by MAP or MLLR for far-field ASR. | |
− | + |
2014年5月5日 (一) 12:52的版本
Accomplished this week
- Found the noisy-training directory and listed the current process.
- Partially got the models by narrow-band noisy-training.
- Perfectly read the code of VAD.
Next Week
- Go on completing the job about integrating the code of VAD with DNN into the framework of standard VAD.
- Decoding on dev93 data set on iteration 1-4 and analyze the results.
- Decoding on the models of narrow-band noisy-training.
- Try to fix the DNN model by MAP or MLLR for far-field ASR.