Objective estimation of the quality of radical noise suppression algorithms
- Authors: Prodeus A.1, Didkovskyi V.S.1
-
Affiliations:
- National Technical University of Ukraine “Kyiv Polytechnic Institute”
- Issue: Vol 59, No 11 (2016)
- Pages: 502-509
- Section: Article
- URL: https://journals.rcsi.science/0735-2727/article/view/176969
- DOI: https://doi.org/10.3103/S0735272716110042
- ID: 176969
Cite item
Abstract
There are compared six noise suppression algorithms with application of objective factors of the speech signal quality, and also with application of through quality factor of the system of automated speech recognition in form of speech recognition accuracy. It is shown that radical noise suppression algorithms are worse than traditional noise suppression algorithms by both restored speech quality and speech recognition accuracy due to essential signal distortion.
About the authors
A. Prodeus
National Technical University of Ukraine “Kyiv Polytechnic Institute”
Author for correspondence.
Email: aprodeus@gmail.com
Ukraine, Kyiv
V. S. Didkovskyi
National Technical University of Ukraine “Kyiv Polytechnic Institute”
Email: aprodeus@gmail.com
Ukraine, Kyiv