Primjena umjetnih neuronskih mreža za strojnu tvorbu hrvatskoga govora

master's thesis

• Title (english): Artificial Neural Networks for Croatian Speech Synthesis
• Author: Eduardo Marić
• Mentor: Marin Vuković (mentor)
• Committee member: Marin Vuković (predsjednik povjerenstva)
• Committee member: Miljenko Mikuc (član povjerenstva)
• Committee member: Krešimir Pripužić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-08, 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: Text-To-Speech; hrvatski jezik; TTS; sequence-to-sequence; strojno učenje; strojna tvorba govora
• Keywords (english): Text-To-Speech; Croatian; machine speech synthesis; artificial neural networks; machine learning; sequence-to-sequence
• Language: croatian
• URN:NBN: urn:nbn:hr:168:173160
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 12:58:35