Information and communication and chemical technologies

Vol. 4 No. 29 (2025) / 2025-12-30 / Number of views: 204

SPEAKER RECOGNITION BASED ON NEURAL NETWORKS USING CHARACTERISTIC SPECTROGRAMS

Authors

Kazakh National Women's Pedagogical University
https://orcid.org/0000-0002-9117-4369
Al-Farabi Kazakh National University
https://orcid.org/0000-0002-6491-8043
Al-Farabi Kazakh National University
https://orcid.org/0000-0002-1993-9566
Kazakh National Women's Pedagogical University
https://orcid.org/0009-0005-1642-9834

Keywords

speech recognition, algorithm, MFCC, spectogram, MLP, AC-SOM

Link to DOI:

https://doi.org/10.58805/kazutb.v.4.29-1115

How to quote

Mekebayev, N., et al. “SPEAKER RECOGNITION BASED ON NEURAL NETWORKS USING CHARACTERISTIC SPECTROGRAMS”. Vestnik KazUTB, vol. 4, no. 29, Dec. 2025, doi:10.58805/kazutb.v.4.29-1115.

Abstract

A neural network-based method is proposed for extracting speaker articulation characteristics. It employs specialized trigram statistics to obtain a representative spectrogram that provides a stable representation of the speaker’s articulation through a linear superposition of short-term spectrograms. To address the issues of slow training and recognition speed in speaker recognition systems on resource-constrained devices, an Adaptive Clustering Self-Organizing Map (AC-SOM) algorithm is introduced, based on the traditional Self-Organizing Map (SOM) neural network. This algorithm automatically adjusts the number of neurons at the competitive layer based on the number of speakers to be recognized, until the number of clusters matches the number of speakers. A dataset comprising characteristic spectrogram patterns from 100 speakers was developed and used for the proposed AC-SOM model, achieving a maximum training time of only 304 seconds and a maximum recognition time of less than 28 milliseconds per sample. Compared to other approaches, the proposed method significantly improves training and recognition speed without sacrificing high recognition accuracy. The promising results indicate that, in contrast to existing speaker recognition techniques, the proposed method better meets the real-time data processing and execution requirements of edge intelligence systems.