Дослідження методів розпізнавання та класифікації мовленнєвого сигналу

Abstract

Diploma work on theme «Research methods of identification and classification of speech signal» by student Semkiv Andrii Volodymyrovych. – Ternopil Ivan Pul'uj National Technical University, Faculty of Computer Information Systems and Software Engineering, Software engineering department, group SPm-61 // Ternopil, 2017. Pages. – 101, pictures. – 13, tables. – 3, slides – 13, add. – 4, bibl.ref. – 48. The aim of the thesis is to study the methods of recognition and classification of the speech signal using computer modeling techniques and process incoming information according to mathematical models developed using Fourier transform. Based on the analysis the advantages and disadvantages of different approaches and methods. Methods and software used in performing of system development: the programming language Java and its libraries, development environment – Netbeans IDE, development environment and simulation of MatLab, flexible methodology (Agile) of software development. Result of work is the optimal method of recognition and classification of the speech signal. In a module software system implemented a series of algorithms that optymizovuyut shortcomings of existing methods.. Keywords: MATHEMATICAL MODEL, COMPUTER SIMULATION, SPEECH SIGNALS, SOFTWARE SYSTEMS, ALGORITHMS, FOURIER TRANSFORM.