Difference between revisions of "2016-07-21"

From cslt Wiki
Jump to: navigation, search
 
Line 1: Line 1:
 
* Daily report
 
* Daily report
  
# Watch lecture video of Graphic Model which was given by Eric Xing in Carnegie Mellon University.
+
# Sibling speaker recognition.
# Use 11,12,13,14 as Gaussian mixture parameter to test the quality of voice conversion.
+
## Data preparation.
## Use 40 utterance to be the training set.
+
# Learn 'machine learning' courase.

Latest revision as of 04:26, 22 July 2016

  • Daily report
  1. Sibling speaker recognition.
    1. Data preparation.
  2. Learn 'machine learning' courase.