NUTQ SIGNALLARINI NORMALLASHTIRISH ALGORITMLARI

Narzullo Mamatov; Xurshid Dusanov

Авторы

Narzullo Mamatov “TIQXMMI” Milliy tadqiqot universiteti
Xurshid Dusanov Muxammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti

Ключевые слова:

Xalaqit, Ovoz tanib olish tizimlari, bo‘sag‘a, Qisqa muddatli energiya, noldan o‘tish chastotasi, frikativ tovushlar, Normallashtirish, Ekstremum

Аннотация

Nutq signalining amplitudasi turli tashqi va ichki omillar ta’sirida o‘zgarishi mumkin. Ushbu maqolada nutq signallarini normallashtirish algoritmlari tahlil qilinib, ularning asosiy tamoyillari, energiya va chastota xususiyatlari, shuningdek, VAD (Voice Activity Detection) algoritmi yordamida nutq sohalarini ajratish usullari ko‘rib chiqilgan. Bundan tashqari, ekstremumlar tarqalishiga asoslangan nutq segmentatsiyasi usuli taklif qilinib, uning samaradorligi neyron tarmoqlar yordamida baholangan. Tadqiqot natijalari shuni ko‘rsatadiki, taklif etilgan yondashuv turli shovqinli muhitlarda ham nutq va fon xalaqitlarini samarali ajrata oladi.

Библиографические ссылки

L. R. Rabiner, R. W. Schafer, Digital Processing of Speech Signals, Prentice-Hall, 1978.

ITU-T Recommendation G.729B, Coding of speech at 8 kbit/s using conjugate-structure algebraic-code-excited linear prediction (CS-ACELP), 1996.

A. Sangwan, J. Hansen, Automatic Voice Activity Detection in Presence of Background Noise Using Neural Networks, IEEE Transactions on Speech and Audio Processing, 2012.

G. Hinton et al., Deep Neural Networks for Acoustic Modeling in Speech Recognition, IEEE Signal Processing Magazine, 2012.

Попов В.И. Основы сотовой связи стандарта GSM // В.И.Попов. – М.: Эко-Трендз, 2005. – 296 с

Юлдошев Ю.Ш. Нутқ сигналларини нормаллаштириш ва соҳаларини ажратиб олиш алгоритми // Мухаммад ал – Хоразмий авлодлари, 3(13) /2020, Б. 24-30.

Mamatov N., Payazov M., Niyozmatova N., Yuldoshev Yu., Mamadalieva N. Definition of Speech Intelligibility of the Uzbek Language International Journal of Innovative Technology and Exploring Engineering (IJITEE)ISSN: 2278-3075, Volume-9 Issue-3, January 2020, DOI: 10.35940/ijitee. B6370.019320

N.S.Mamatov, O.J.Babomuradov, X.T. Dusanov Automatic speaker recognition through voice using deep neural networks. Journal of Computer Science Engineering and Information Technology Research (JCSEITR) ISSN (Print): 2250-2416; ISSN (Online): Applied Vol. 14, Issue 1; Jun 30 2024, 13-20.