QUARTZNET MODEL IN AUTOMATIC SPEECH RECOGNITION

Нарзилло, Маматов, Шерзод, Абдуллаев, Юсуф, Юлдошев, Адхам, Гомидов

Al-Farg'oniy avlodlari · 2026-yil

Annotatsiya

This article describes the research conducted by training the neural network model proposed by NVIDIA in speech recognition with a speech dataset of the Uzbek language. Currently, various models of neural networks are widely used in the creation of automatic speech recognition systems. This leads to a sharp increase in the quality of speech recognition. Existing speech recognition systems are designed to work on the basis of various neural network models. This article is devoted to the application of one of such models in automatic speech recognition, and it presents information on the quartznet model and its use.

Maqola ma’lumotlari
MualliflarНарзилло, Маматов, Шерзод, Абдуллаев, Юсуф, Юлдошев, Адхам, Гомидов
JurnalAl-Farg'oniy avlodlari
Nashr sanasi2026-03-27
Son1
Betlar353-355
TilRus

Kalit so‘zlar

automatic speech recognition, neural network model, QuartzNet, spectrogram, error function, optimizer, автоматическое распознавание речи, модель нейронной сети, QuartzNet, спектрограмма, функция ошибки, оптимизатор, nutqni avtomatik tanib olish, neyron tarmoq modeli, QuartzNet, spektogramma, xatolik funksiyasi, optimizator.

Ilmiy soha

Al-Farg'oniy avlodlari jurnalidan boshqa maqolalar

Al-Farg'oniy avlodlari — barcha maqolalar