Glasovno upravljanje televizije z uporabo sistema Sphinx-4 : diplomsko delo

Cetinski, Katja (author), Kodek, Dušan (mentor)

Namen diplomske naloge je bila izdelava sistema za govorno upravljanje televizije. Za razpoznavo ukazov sem uporabila sistem Sphinx-4. Posebej za ta namen sem izdelala lastno govorno bazo, saj prosto dostopnih posnetkov slovenskega govora močno primanjkuje. S pomočjo orodja NetBeans sem nato v programskem jeziku Java razvila aplikacijo, ki razpozna določen ukaz in ga preko serijskih vrat pošlje na razvojno ploščico Arduino. Glede na prejet podatek pa Arduino nato pošlje primeren IR signal televiziji. Če povzamem vsebino diplomske naloge se na začetku posvetimo predvsem teoretičnemu ozadju. V uvodu se seznanimo s pojmom razpoznava govora ter s splošnim sistemov za razpoznavo govora. Sledijo teoretične osnove o prikritih modelih Markova, kateri se uporabljajo kot eden izmed pristopov pri razpoznavi govora. V nadaljevanju se seznanimo s sistemom Sphinx-4, sistemom za učenje SphinxTrain in na koncu še z razvojno ploščico Arduino. S tem izvemo ključne stvari, ki so potrebne za razumevanje delovanja takšnega sistema. V drugi polovici si lahko ogledamo podrobno shemo sistema in se obenem seznanimo s praktično izdelavo sestavnih delov. Na koncu si v razpredelnici ogledamo rezultate testiranj pri dejanski uporabi sistema. Sledijo priloge, ki vsebujejo programsko kodo celotnega sistema. Celotna programska koda se nahaja na zgoščenki na zadnji strani diplome, nekaj pomembnejših delov pa tudi v poglavju priloge v obliki teksta.

• Language: Slovenian
• Keywords: razpoznavanje govora, Sphinx-4, televizija, Arduino, računalništvo, univerzitetni študij, diplomske naloge
• Work type: Undergraduate thesis
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science
• Publisher: [K. Cetinski]
• Year: 2010
• Number of pages: 42 f.
• PID: 20.500.12556/RUL-69607
• UDC: 004(043.2)
• COBISS.SI-ID: 8068180
• Publication date in RUL: 10.07.2015

Secondary language

• Language: English
• Title: Voice controlled television set using system Sphinx-4

Abstract

The main purpose of this diploma thesis was development of a system for voice controlled TV set. I used Sphinx-4 system for recognition of television commands. Because there is a big problem of getting free Slovenian speech recordings, I created my own speech database. I used NetBeans IDE for developing my application, which is written in Java programming language. Application recognizes a certain voice command and then sends corresponding data to Arduino development board. According to received data, Arduino sends appropriate IR signal to television. The content of diploma thesis is divided into two parts. First part is mainly theoretical. We learn the basis of speech recognition and general recognition system. This is followed by theoretical basis of Hidden Markov Models which are one of the principles used in speech recognition systems. Next we learn about Sphinx-4 system and SphinxTrain. The last one is used for acoustic model learning. The first part of diploma thesis ends with a description of Arduino development board. That way we learn the basic things that helps us understand the whole system. The second part describes the development of a speech controlled television system. It includes testing and conclusion. Some smaller parts of source code are written in contents chapter, others can be found on a CD that is part of the thesis.

• Keywords: speech recognition, Sphinx-4, television, Arduino, computer science, diploma