A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE)

Нуримов, П.Б., Бабомурадов, О.Ж.

Рақамли технологияларнинг назарий ва амалий масалалари · 2026-yil

Annotatsiya

This paper proposes a new feature extraction method for speaker recognition, called Delta-Gated Spike Encoding (DGSE). The proposed approach combines log-Mel spectrograms, temporal delta, adaptive thresholding, an energy gate, and positive/negative spike encoding stages. The goal is to extract informative time-frequency changes from the acoustic signal and form a sparse representation suitable for subsequent spiking or energy-efficient models. Experiments were conducted on the VoxCeleb1 dataset using a three-stage parametric search procedure. The results of the initial coarse search, the subsequent extended search, and the final fine search were compared. The best result was obtained with the parameters alpha = 1.0, beta = 0.05, and energy_thr = -5.25. Under these settings, the method achieved total spike rate = 0.079585, sparsity = 0.920415, and gate open rate = 0.718533. The obtained results show that the DGSE method preserves informative parts of the signal while ensuring high sparsity. This makes it a promising solution for resource-constrained devices and CNN-SNN hybrid speaker recognition systems.

Maqola ma’lumotlari
MualliflarНуримов, П.Б., Бабомурадов, О.Ж.
JurnalРақамли технологияларнинг назарий ва амалий масалалари
NashriyotТАТУ Самарқанд филиали
ISSN2181-3086, 2181-3094
Nashr sanasi2026-05-15
Jild9
Son2
Betlar86-91
TilIngliz
Ilmiy sohaTexnika
DOI10.62132/ijdt.v9i2.379
Indeksga qo‘shilgan2026-08-26

DOI: 10.62132/ijdt.v9i2.379 · Maqolaning asl sahifasi

Kalit so‘zlar

распознавание говорящего, извлечение признаков, log-Mel, spike-кодирование, разреженность, нейроморфные вычисления, VoxCeleb1, DGSE, speaker recognition, feature extraction, log-Mel, spike encoding, sparsity, neuromorphic computing, VoxCeleb1, DGSE

Ilmiy soha

Texnika

Iqtibos keltirish

APAНуримов, П.Б., & Бабомурадов, О.Ж. (2026). A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE). Рақамли технологияларнинг назарий ва амалий масалалари, 9(2), 86-91. https://doi.org/10.62132/ijdt.v9i2.379
GOST (OAK)Нуримов, П.Б., Бабомурадов, О.Ж. A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE) // Рақамли технологияларнинг назарий ва амалий масалалари. – 2026. – T. 9, № 2. – P. 86-91. – DOI: 10.62132/ijdt.v9i2.379.
MLAНуримов, П.Б., and Бабомурадов, О.Ж. “A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE).” Рақамли технологияларнинг назарий ва амалий масалалари, 9(2), 86-91, 2026. https://doi.org/10.62132/ijdt.v9i2.379
ChicagoНуримов, П.Б., and Бабомурадов, О.Ж. “A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE).” Рақамли технологияларнинг назарий ва амалий масалалари, 9(2), 86-91 (2026). https://doi.org/10.62132/ijdt.v9i2.379
HarvardНуримов, П.Б., and Бабомурадов, О.Ж (2026) ‘A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE)’, Рақамли технологияларнинг назарий ва амалий масалалари, 9(2), 86-91. https://doi.org/10.62132/ijdt.v9i2.379
BibTeX
@article{article2026,
  title = {A method for extracting sparse and energy-efficient feature sets based on Delta-Gated Spike Encoding (DGSE)},
  author = {Нуримов, П.Б. and Бабомурадов, О.Ж.},
  journal = {Рақамли технологияларнинг назарий ва амалий масалалари},
  year = {2026},
  volume = {9},
  number = {2},
  pages = {86-91},
  doi = {10.62132/ijdt.v9i2.379},
  url = {https://doi.org/10.62132/ijdt.v9i2.379}
}

Boshqa maqola uchun iqtibos tayyorlash

Рақамли технологияларнинг назарий ва амалий масалалари jurnalidan boshqa maqolalar

Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar · 2026-yil arxivi

Нуримов, П.Б. — boshqa maqolalari

Texnika sohasidagi boshqa maqolalar

Texnika sohasidagi OAK jurnallari