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

Project

General

Custom queries

Profile

Actions
Copy link

Task #3855

closed

Task #3680: RA4a - Automatic error prediction

Task #3698: Experiment with one-class clasification for join cost enhancements

More data for artefacts collection

Added by Tihelka Dan about 9 years ago. Updated over 8 years ago.

Status:
Postponed
Priority:
Normal
Assignee:
Grůber Martin
Target version:
RA4: Automatic error prediction and signal modification
Start date:
06.04.2016
Due date:
10.04.2016
% Done:

0%

Estimated time:

Description

We need more data for listening tests. Especially we need to increase the coverage of rare vowels. Currently we have:

phone total OK artefact
a 78 60 18
e 82 46 36
i 49 30 19
o 92 50 42
u 23 22 1
A 123 17 104
E 4 4 0
I 23 17 6
O 0 0 0
U 4 4 0

We can either try to find additional words in the corpus (shorter, though), or build "artificial" words by joining two halves of words (or words transitions) from the corpus.

Files

Download all files
prepare_words.py (26.8 KB) prepare_words.py Script to select words of the appropriate length from ASF Tihelka Dan, 06.04.2016 13:39
asf2json_mix.py (5.06 KB) asf2json_mix.py Tihelka Dan, 09.08.2016 15:15
#1

Updated by Tihelka Dan about 9 years ago

#2

Updated by Matoušek Jindřich about 9 years ago

  • Target version changed from RA1: Analysis of artifacts in synthetic speech to RA4: Automatic error prediction and signal modification
#3

Updated by Grůber Martin almost 9 years ago

  • Status changed from New to Assigned
  • Assignee changed from Grůber Martin to Tihelka Dan
#4

Updated by Tihelka Dan over 8 years ago

#5

Updated by Grůber Martin over 8 years ago

  • Status changed from Assigned to Postponed
Actions
Copy link

Also available in: Atom PDF