Izvestiya of Saratov University.

Mathematics. Mechanics. Informatics

ISSN 1816-9791 (Print)
ISSN 2541-9005 (Online)


For citation:

Savin A. N., Timofeeva N. E., Geraskin A. S., Mavlutova Y. A. The Development of Software Components for Streaming Audio Content Filtering Through the Use of Hidden Markov Models. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, 2015, vol. 15, iss. 3, pp. 340-350. DOI: 10.18500/1816-9791-2015-15-3-340-350, EDN: UKIVHN

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Published online: 
11.09.2015
Full text:
(downloads: 224)
Language: 
Russian
Heading: 
UDC: 
004.934
EDN: 
UKIVHN

The Development of Software Components for Streaming Audio Content Filtering Through the Use of Hidden Markov Models

Autors: 
Savin Aleksandr Nikolaevich, Saratov State University
Timofeeva Nadezhda Evgen'evna, Saratov State University
Geraskin Aleksej Sergeevich, Saratov State University
Mavlutova Yuliya Albertovna, Saratov State University
Abstract: 

The results of the development of efficient algorithms for streaming voice recognition using stochastic models based on the use of hidden Markov models are shown in this work. The article provides basic theoretical information for the hidden Markov model of the discrete system and the necessary parameters to define it are distinguished. Also there are three main tasks considered that need to be solved for the successful application of hidden Markov models in speech recognition systems. The algorithm of the method of Baum–Welch aimed at clarifying the parameters of the model and the Viterbi algorithm of selection of the most likely sequence of states of the system are given. These two methods are implemented in the environment of graphical programming LabVIEW in the form of software modules that implement the construction of the hidden Markov models of individual words, using the method of Baum–Welch and recognition of these words on the basis of the Viterbi method. It is supposed to use these modules to implement streaming audio content filtering in digital communication systems.

References: 
  1. Гоноровский И. С., Демин М. П. Радиотехнические цепи и сигналы. М. : Дрофа, 2006. 719 с.
  2.  Сергиенко А. Б. Цифровая обработка сигналов. СПб. : Питер, 2007. 750 с.
  3.  Рабинер Л. Р. Скрытые Марковские модели и их применение в избранных приложениях при распознавании речи // ТИИЭР. 1989. Т. 77. С. 86–120.
  4.  Narada Warakagoda A Hybrid ANN-HMM ASR system with NN based adaptive preprocessing M. Sc. thesis. URL: http://jedlik.phy.bme.hu/ gerjanos/HMM/hoved.html (Accessed: 21.12.2012).
  5. Портал компании National Instruments Russia. URL: http://www.labview.ru (дата обращения: 25.12.2012).
Received: 
26.04.2015
Accepted: 
28.08.2015
Published: 
30.09.2015