Integracija modula za pretvorbu teksta u govor na hrvatskom jeziku na NAO robota

undergraduate thesis

• Title (english): Integration of Text to Speech Module for Croatian Language on NAO Robot
• Author: Brigita Vrbanec
• Mentor: Zdenko Kovačić (mentor)
• Committee member: Zdenko Kovačić (predsjednik povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Committee member: Frano Petric (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-09-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je integracija modula za pretvorbu teksta u govor na hrvatskom jeziku na NAO robota. Razmatrana je integracija modula tvrtke AlfaNum koja je izradila prvi sustav za sintezu govara na hrvatskom i srodnim južnoslavenskim jezicima. Njihov sustav, zahvaljujući predstavljenim naprednim heurističkim algoritmima, daje prirodan zvuk i tečan govor. Ukratko je objašnjen način rada NAOqi modula i predstavljena osnovna funkcionalnost razvijenog TTS modula. Ovaj TTS modul pokreće se na robotu i moguće mu je pristupiti direktno s robota ili, preko mreže, s računala. Modul trenutačno reproducira zvučni zapis do kojeg mu se preda put, a kada bude dostupan softver za Linux operacijski sustav, predavat će mu se tekst koji će on slati na sintezu i reproducirati dobiveni zvučni zapis.

Abstract (english)

The subject of this thesis is the integration of a Croatian language text to speech module on a NAO robot. The considered text to speech module is a commercially available product, developed by the company AlfaNum. It provides a complete speech synthesis system for Croatian and related South Slavic languages. Using advanced heuristic algorithms described in this thesis, it provides natural sound and fluent speech. We briefly explain the principle of operation of Naoqi modules and present the basic functionality of the implemented TTS module. The TTS module runs on the robot and can be accessed directly from the robot, or over the network from a client computer. The module currently plays the audio file from the provided path. Full text to speech functionality is planned, pending the successful porting of the AlfaNum TTS module to the Linux operating system.

• Keywords: NAO robot; pretvorba teksta u govor; sinteza govora; hrvatski jezik
• Keywords (english): NAO robot; text to speech; speech synthesis; Croatian language
• Language: croatian
• URN:NBN: urn:nbn:hr:168:439605
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 14:23:40