43

Ushbu ishda ovoz orqali tanib olish masalasini yechish uchun qo‘llaniladigan usullar sharhi keltirilgan. Tanib olish tizimlarining barqaror tuzilishiga alohida e’tibor qaratilgan. Shuningdek, belgilarni ajratib olishning eng keng tarqalgan usullari (masalan, MFCC va LPCC)ning qisqacha tavsifi hamda tasniflash usullari (vektorli kvantlash usuli, Gauss qorishmalari modeli, tayanch vektorlar usuli) haqida ma’lumot berilgan. Tanib olish tizimlarini baholash usullari va bunday baholash natijalarini taqdim etish yo‘llari muhokama qilingan.

  • Internet ҳавола
  • DOI
  • UzSCI тизимида яратилган сана 20-01-2025
  • Ўқишлар сони 43
  • Нашр санаси 28-12-2024
  • Мақола тилиO'zbek
  • Саҳифалар сони130-136
Ўзбек

Ushbu ishda ovoz orqali tanib olish masalasini yechish uchun qo‘llaniladigan usullar sharhi keltirilgan. Tanib olish tizimlarining barqaror tuzilishiga alohida e’tibor qaratilgan. Shuningdek, belgilarni ajratib olishning eng keng tarqalgan usullari (masalan, MFCC va LPCC)ning qisqacha tavsifi hamda tasniflash usullari (vektorli kvantlash usuli, Gauss qorishmalari modeli, tayanch vektorlar usuli) haqida ma’lumot berilgan. Tanib olish tizimlarini baholash usullari va bunday baholash natijalarini taqdim etish yo‘llari muhokama qilingan.

English

This paper provides an overview of methods used for voice recognition. Special attention is given to the robust structure of recognition systems. Additionally, a brief description of the most widely used feature extraction methods (such as MFCC and LPCC) and classification techniques (vector quantization method, Gaussian mixture model, support vector method) is presented. Methods for evaluating recognition systems and approaches for presenting the results of such evaluations are discussed.

№ Ҳавола номи
1 Samatov, R., & Xalilova, G. (2024). Searching for a free Будков В.Ю., Прищепа М.В., Ронжин А.Л., Марков К. Многоканальная система анализа речевой активности участников совещания // Третий междисциплинарный семинар «Анализ разговорной русской речи» АР3. 2009. СПб. 2009. С. 57-62.
2 Рабинер Л.Р., Шафер Р.В. Цифровая обработка речевых сигналов / Пер. с англ. М. : Радио и связь, 1981. 496 с.
3 Садыхов Р.Х., Ракуш В.В. Модели гауссовых смесей для верификации диктора по произвольной речи // Доклады БГУИР. Минск, 2003. №
4 С. 95–103. 4. Сорокин В.Н., Цыплихин А.И. Верификация диктора по спектрально-временным параметрам речевого сигнала // Информационные процессы. 2010. Т. 10, № 2. С. 87-104.
5 Arya S., Mount D.M., Netanyahu N.S., Silverman R., Wu A. An optimal algorithm for approximate nearest neighbor searching in fixed dimensions // Journal of the ACM. 1998. V. 45, N 6. P. 891–923
6 Campbell J.P., Speaker Recognition: A Tutorial // Proceedings of the IEEE. 1997. V. 85, N 9. P. 1437-1462.
7 Martin A., Doddington G., Kamm T., Ordowski M., Przybocki M. The det curve in assessment of detection task performance // Proc. of Eurospeech. 1997. V. 4. P. 1895- 1898.
8 Martin A., Przybocki M. The NIST 1999 Speaker Recognition Evaluation - An Overview // Digital Signal Processing. 2000. V. 10.
9 Navratil J., Klusacek D. On linear DETs // Internat. Conf. on Acoustics, Speech, and Signal Processing (ICASSP-07). 2007.
10 Paredes R., Vidal E., Casacuberta F. Local features for speaker recognition // SPR 2004. International Workshop on Statistical Pattern Recognition. LNCS 3138 of Lecture Notes in Computer Science. 2004. P. 1087-1095.
11 Platt J.C. Fast Training of Support Vector Machines using Sequential Minimal Optimization // Advances in Kernel Methods / Ed. by B. Scholkopf, C.C. Burges, A.J. Smola. MIT Press, 1999. P. 185–208.
12 Reynolds D.A. An Overview of Automatic Speaker Recognition Technology // The International Conference on Acoustics, Speech, and Signal Processing ICASSP 02. 2002. P. 4072–4075.
Кутилмоқда