Contribution from the accuracy of phoneme recognition to the quality of automatic recognition of Russian speech

The dependence of the quality of automatic recognition of Russian speech on the accuracy of feature descriptions and their distribution model is considered. A list of eight phonemes is given whose accuracy of recognition makes the greatest contribution to the quality of speech recognition.

Saved in:
Bibliographic Details
Published in:Moscow University computational mathematics and cybernetics 2016-04, Vol.40 (2), p.89-95
Main Author: Karpukhin, I. A.
Format: Article
Language:English
Subjects:
Mathematics
Mathematics and Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The dependence of the quality of automatic recognition of Russian speech on the accuracy of feature descriptions and their distribution model is considered. A list of eight phonemes is given whose accuracy of recognition makes the greatest contribution to the quality of speech recognition.
ISSN:0278-6419
1934-8428
DOI:10.3103/S0278641916020060