Sustav za automatsko prepoznavanje govora s ciljem prevođenja

undergraduate thesis

• Title (english): Automatic speech recognition system for translation purposes
• Author: Filip Mađarić
• 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: 2024-06-27, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

U današnje vrijeme, tehnologije prepoznavanja govora sve se više koriste u svakodnevnom životu. Neke od najpoznatijih tehnologija, STT (Speech-To-Text) i TTS (Text-To-Speech), doživjeli su veliki porast u implementaciji kroz posljednjih nekoliko godina, posebno s pojavom tehnologija kao što su pametni asistenti. Automatsko prepoznavanje govora je vrlo izazovan proces, no korištenjem raznih rješenja, kao i jednog od najpopularnijih programskih jezika – Python, taj proces se može pojednostavniti. Svrha ovog završnog rada je istraživanje tehnologije automatskog prepoznavanja govora, što je realizirano podjelom rada u teorijski i praktični dio. Teorijski dio pokriva neka recentna istraživanja na temu tehnologija prepoznavanja govora, kao i objašnjenja navedenih tehnologija, alata, korištenog programskog jezika i korištenih modula unutar istog. U tehničkom dijelu obrađena je izrada programa koja koristi tehnologiju automatskog prepoznavanja govora, kao i tehnologiju sinteze govora iz teksta. Sustav prikazan u praktičnom dijelu koristi tehnologiju prepoznavanja govora s ciljem prevođenja izgovorenih informacija, te iščitavanja istih na drugom jeziku.

Abstract (english)

In today’s world, speech recognition technologies are being increasingly used in everyday life. Some of the most well-known technologies, STT (Speech-To-Text) and TTS (Text-To-Speech), have seen a significant increase in implementation over the past few years, especially with the emergence of technologies such as smart assistants. Automatic speech recognition is a highly challenging process, but by using various solutions, as well as one of the most popular programming languages – Python, this process can be simplified. The purpose of this bachelor thesis is to explore automatic speech recognition technology, which is realized by dividing the paper into a theoretical and practical part. The theoretical part covers some recent research on the topic of speech recognition technologies, as well as explanations of the mentioned technologies, tools, the programming language used, and the modules used within it. The technical part involves the development of a program that utilizes automated speech recognition technology, as well as speech synthesis technology. The system shown in the practical part uses automatic speech recognition technology for the purpose of translating spoken information and reading said information aloud in a different language.

• Keywords: Automatsko prepoznavanje govora; Sinteza govora; Text to speech; Speech to text; Strojno prevođenje; Python
• Keywords (english): Automatic speech recognition; Speech synthesis; Text to speech; Speech to text; Machine translation; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:131:442661
• Study programme: Title: Information Sciences; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to authenticated users
• Created on: 2024-06-27 20:12:20