prikaz prve stranice dokumenta Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora
No public access
master's thesis
Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:173160
Marić, Eduardo
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Marić, E. (2020). Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:173160

Marić, Eduardo. "Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:173160

Marić, Eduardo. "Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:173160

Marić, E. (2020). 'Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 24 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:173160

Marić E. Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 June 24] Available at: https://urn.nsk.hr/urn:nbn:hr:168:173160

E. Marić, "Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:173160

Metadata
TitlePrimjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora
Title (english)Artificial Neural Networks for Croatian Speech Synthesis
AuthorEduardo Marić
MentorMarin Vuković (mentor)
Committee memberMarin Vuković (predsjednik povjerenstva)
Committee memberMiljenko Mikuc (član povjerenstva)
Committee memberKrešimir Pripužić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-08, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Razvojem metoda strojnoga učenja, uključivo sa umjetnim neuronskim mrežama, otvorile su se prilike za velikim skokovima u strojnoj tvorbi govora, posebice u sustavima koji to čine u objedinjenome ciklusu, end-to-end Text-To-Speech sustavima. Upravo zbog generalne prirode takvih modela, pristup korištenjem umjetnih neuronskih mreža omogućuje primjenu na razne jezike bez značajnih promjena u arhitekturi te pristupu samoga sustava. Sustav Tacotron 2, Mozilla TTS implementacijom, pokazao se kao idealan odabir primjenjiv na korpus hrvatskoga jezika. Ta je pretpostavka u ovome radu i dokazana, uspješnom tvorbom hrvatskoga govora uz minorne ili pak nepostojeće promjene u načinu izvođenja sustava. No, kao preduvjet kvalitetnim rezultatima, objašnjeni su pristupi obradi te pripremi podataka, te pokazana ovisnost kvalitete u kontekstu razumljivosti o količini podataka.
Abstract (english)
With the appearance and development of machine learning models, and an emphasis on artificial neural networks, large leaps in the machine generation of human speech, or otherwise, have been made, especially when considering an end-to-end approach. It is because of the learning nature of the models that artificial neural networks exceed expectations when applied to different sets of data, in this case different languages. Tacotron 2, and the Mozilla TTS implementation, has proven to be the ideal choice for the synthesis of croatian speech, due to the earlier mentioned advantages. That hypothesis has been proven in this paper by successfully synthesizing croatian speech with little to no adjustments to the implementation itself, especially when it comes to the architecture. As a prerequisite for a working system, we have shown that the quality of generated speech, within the context of understandability, is dependant on the size of the dataset on which the model is being trained, while on the other hand predicting that the naturalness of speech rather depends more on the quality of the recordings themselves.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:173160
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 12:58:35