Govorne tehnologije u programskom jeziku Python za hrvatski jezik

master's thesis

• Title (english): Speech technologies in the Python programming language for the Croatian language
• Author: Lucia Sirovec
• Mentor: Ivan Dunđer (mentor)
• Committee member: Sanja Seljan (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Ivan Dunđer (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2023-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

Govorne tehnologije, posebno govor-u-tekst (engl. speech-to-text), zahvaljujući razvitku umjetne inteligencije i posebno neuronskih mreža iznimno su napredovale posljednjih godina i postale ključnim alatom u mnogim područjima, kao i u svakodnevici.
Cilj ovog diplomskog rada je opisati kako funkcionira tehnologija pretvaranja govora u tekst. Rad se sastoji od dva dijela. U prvom, teorijskom dijelu bit će navedeni i objašnjeni neki od ključnih izazova s kojima se susrećemo pri stvaranju sustava pretvorbe govora u tekst. Također će se navesti ograničenja i izazovi koji su povezani s tehnologijom pretvaranja govora u tekst te će se opisati razni alati koje je moguće koristiti za pretvorbu govora u tekst. Drugi, praktični dio rada bavit će se korištenjem algoritama za pretvorbu govora u tekst. U radu će se napraviti usporedna analiza i testiranje algoritama u programskom jeziku Python za hrvatski jezik.

Abstract (english)

Speech technologies, especially speech-to-text, thanks to the development of artificial intelligence and especially neural networks, have progressed tremendously in recent years and have become a key tool in many areas, as well as in everyday life.
The aim of this master’s thesis is to describe how speech-to-text technology works. The paper consists of two parts. In the first, theoretical part, some of the key challenges we face when creating a speech-to-text conversion system will be listed and explained. It will also outline the limitations and challenges associated with speech-to-text technology and describe the various tools that can be used for speech-to-text. The second, practical part of the paper will deal with the use of algorithms for converting speech into text. In the paper, a comparative analysis and testing of algorithms in the programming language Python for the Croatian language will be done.

• Keywords: govor u tekst; govorne tehnologije; Python
• Keywords (english): speech-to-text; speech technologies; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:131:369145
• Study programme: Title: Information Sciences; specializations in: Archivistics Study, Library Science, Information Sciences (research), Information Sciences (teaching), Museology and heritage management, Informatology; Course: Information Sciences (teaching); Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra edukacije informatike (magistar/magistra edukacije informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-07-11 15:36:40