• Login
    • en
    • ru
    • uz
  • Current
  • Archives
    • About the Journal
    • Submissions
    • Privacy Statement
    • Contact
Youtube Facebook Instagram Telegram

Latest publications

  • Atom logo
  • RSS2 logo
  • RSS1 logo

Information

  • For Readers
  • For Authors
  • For Librarians
  1. Home
  2. Search
Advanced filters

Search Results

Found one item.

Application of the kohonen map in speech processing and its efficiency evaluation

Nilufar Niyozmatova, Kuanysh Djalelov, Barno Abdullaeva (Author)
This study proposes a novel approach based on the Kohonen map for denoising speech signals. In this method, noisy clusters were identified using the Kohonen map based on speech frequency and energy characteristics, while the "Minimum Statistics Noise Estimation" method was used to estimate the noise level. This approach allowed for stable results even at high noise levels. As features, MFCC was used for low noise levels, while the Log-Mel spectrogram was employed for high noise levels. Experiments were conducted at various noise levels (1%, 5%, 10%, 15%, 20%, 25% white noise), and the results were evaluated using the PESQ (Perceptual Evaluation of Speech Quality) metric. The proposed approach demonstrated that combining an energy-based criterion with frequency characteristics for identifying noisy clusters significantly improves speech quality.
25-08-2025
  • PDF (Uzbek)
201-204 0 0
1 - 1 of 1 items
© Copyright 2025 Contemporary problems of intelligent systems All Rights Reserved | Developed by in Science | Site create by in Designer