“2016-05-03 To 2016-05-09”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“20160504 Confirm 'voice conversion' as my major direction. Get several literature and tool kits to be the studying source for the next two weeks. Learn how to use '...”为内容创建页面)
 
 
第1行: 第1行:
20160504
+
*20160504
  
Confirm 'voice conversion' as my major direction.
+
#Confirm 'voice conversion' as my major direction.
Get several literature and tool kits to be the studying source for the next two weeks.
+
#Get several literature and tool kits to be the studying source for the next two weeks.
Learn how to use 'putty' and get some message about how to study and work in our lab.
+
#Learn how to use 'putty' and get some message about how to study and work in our lab.
Operate the 'gmm_vc' successfully.
+
#Operate the 'gmm_vc' successfully.
20160506
+
*20160506
  
Read literature about 'Exemplar-Based Sparse Representation with Residual Compensation for Voice Conversion'.
+
#Read literature about 'Exemplar-Based Sparse Representation with Residual Compensation for Voice Conversion'.
Read literature about 'Sparse representation for frequency warping based voice conversion'.
+
#Read literature about 'Sparse representation for frequency warping based voice conversion'.
Read literature about 'Correlation-based frequency warping for voice conversion'.
+
#Read literature about 'Correlation-based frequency warping for voice conversion'.
  
20160507
+
*20160507
  
Read literature about 'Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory'.
+
#Read literature about 'Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory'.
Run and understand the first part and the second part of 'gmm_vc' toolkit.
+
#Run and understand the first part and the second part of 'gmm_vc' toolkit.
  
20160508
+
*20160508
  
Run and understand the third part of the 'gmm_vc' toolkit.
+
#Run and understand the third part of the 'gmm_vc' toolkit.
Understand how a wave file can be 'analysized' to mcc and pitch, and how mcc and pitch can also be used to synthesize the original wav.
+
#Understand how a wave file can be 'analysized' to mcc and pitch, and how mcc and pitch can also be used to synthesize the original wav.
Run the toolkit of sptk3.8 to implement the transform from mcc to wav.
+
#Run the toolkit of sptk3.8 to implement the transform from mcc to wav.
Try to finish the whole conversion process.
+
#Try to finish the whole conversion process.

2016年5月20日 (五) 01:47的最后版本

  • 20160504
  1. Confirm 'voice conversion' as my major direction.
  2. Get several literature and tool kits to be the studying source for the next two weeks.
  3. Learn how to use 'putty' and get some message about how to study and work in our lab.
  4. Operate the 'gmm_vc' successfully.
  • 20160506
  1. Read literature about 'Exemplar-Based Sparse Representation with Residual Compensation for Voice Conversion'.
  2. Read literature about 'Sparse representation for frequency warping based voice conversion'.
  3. Read literature about 'Correlation-based frequency warping for voice conversion'.
  • 20160507
  1. Read literature about 'Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory'.
  2. Run and understand the first part and the second part of 'gmm_vc' toolkit.
  • 20160508
  1. Run and understand the third part of the 'gmm_vc' toolkit.
  2. Understand how a wave file can be 'analysized' to mcc and pitch, and how mcc and pitch can also be used to synthesize the original wav.
  3. Run the toolkit of sptk3.8 to implement the transform from mcc to wav.
  4. Try to finish the whole conversion process.