Project management of NTIS P1 Cybernetic Systems and Department of Cybernetics | WiKKY

Project

General

Profile

Actions
Copy link

Task #3693

closed

Task #3672: RA1d - Automatic cleaning of speech corpora

Task #3690: Annotation error detection

Influence of the number of normal examples used for training on detection accuracy

Added by Matoušek Jindřich almost 9 years ago. Updated over 8 years ago.

Status:
Closed
Priority:
Normal
Assignee:
Matoušek Jindřich
Target version:
RA1: Analysis of artifacts in synthetic speech
Start date:
01.02.2016
Due date:
15.03.2016
% Done:

100%

Estimated time:
8.00 h

Description

Find out influence of the number of normal examples used for training on detection accuracy

Actions
Copy link
 #1

Updated by Matoušek Jindřich almost 9 years ago

  • Status changed from New to Assigned
  • % Done changed from 0 to 30

Script preparation

Actions
Copy link
 #2

Updated by Matoušek Jindřich almost 9 years ago

  • % Done changed from 30 to 40
Actions
Copy link
 #3

Updated by Matoušek Jindřich almost 9 years ago

  • % Done changed from 40 to 50

Experiments with the number of normal examples used in cross validation.

Actions
Copy link
 #4

Updated by Matoušek Jindřich almost 9 years ago

  • % Done changed from 50 to 70

Starting experiments with the number of normal examples used for training of single estimators

Actions
Copy link
 #5

Updated by Matoušek Jindřich over 8 years ago

  • Status changed from Assigned to Closed
  • % Done changed from 70 to 100

Experiments carried out also for voting detector.

Actions
Copy link

Also available in: Atom PDF