Neuromorphic processor with hardware learning based on a convolutional neural network for audio spectrogram analysis

Petrov M.O., Ryndin E.A., Andreeva N.V.
 pdf (4052K)

This paper proposes an architectural solution for organizing a convolutional neural network (CNN) oriented towards hardware implementation on edge devices under limited resources. To this goal, an approach to compressing spectrograms to a given size (28 × 28) is proposed using discretization, monoconversion, windowed Fourier transform, and two-dimensional interpolation. A balanced convolution procedure is developed based on compact convolutional filters, the size of which provides the balance between computational complexity and accuracy required for edge devices. An algorithm that enables convolution operations and calculation of the error function gradient in the convolutional layer in a single cycle ensuring increased performance in both inference and training modes of the CNN is proposed. The tradeoff between network trainability and its resistance to overfitting is optimized by applying the Dropout regularization method with a dropout coefficient of 0.5 for the fully connected layer.

The effectiveness of the proposed solution was demonstrated using the example of recognizing audio spectrograms of car and airplane engine sounds. The CNN was trained on a balanced dataset consisting of 7160 audio recordings. The trained network demonstrated high recognition accuracy (95%), low loss values (< 0.2), and balanced precision/recall/F-metric, demonstrating the effectiveness of the developed CNN model.

Keywords: neuromorphic processor, hardware-assisted learning mode, audio spectrogram, convolutional neural network
Citation in English: Petrov M.O., Ryndin E.A., Andreeva N.V. Neuromorphic processor with hardware learning based on a convolutional neural network for audio spectrogram analysis // Computer Research and Modeling, 2026, vol. 18, no. 1, pp. 81-99
Citation in English: Petrov M.O., Ryndin E.A., Andreeva N.V. Neuromorphic processor with hardware learning based on a convolutional neural network for audio spectrogram analysis // Computer Research and Modeling, 2026, vol. 18, no. 1, pp. 81-99
DOI: 10.20537/2076-7633-2026-18-1-81-99
URL: http://crm-en.ics.org.ru/journal/article/3689/
Creative Commons License This work is licensed under a Creative Commons Attribution-NoDerivs 3.0 Unported License.

Copyright © 2026 Petrov M.O., Ryndin E.A., Andreeva N.V.

Indexed in Scopus

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the RSCI

International Interdisciplinary Conference "Mathematics. Computing. Education"

Website Copyright © 2009–2026 Institute of Computer Science