prikaz prve stranice dokumenta Akustičko modeliranje govora za potrebe sinteze govora
Access restricted to students and staff of home institution
master's thesis
Akustičko modeliranje govora za potrebe sinteze govora
Rijeka: University of Rijeka, Faculty of Engineering, 2020. urn:nbn:hr:190:035385
Polonijo, Toni
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Intelligent Computing Systems

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Polonijo, T. (2020). Akustičko modeliranje govora za potrebe sinteze govora (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:035385

Polonijo, Toni. "Akustičko modeliranje govora za potrebe sinteze govora." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:035385

Polonijo, Toni. "Akustičko modeliranje govora za potrebe sinteze govora." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:035385

Polonijo, T. (2020). 'Akustičko modeliranje govora za potrebe sinteze govora', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 01 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:035385

Polonijo T. Akustičko modeliranje govora za potrebe sinteze govora [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2020 [cited 2024 November 01] Available at: https://urn.nsk.hr/urn:nbn:hr:190:035385

T. Polonijo, "Akustičko modeliranje govora za potrebe sinteze govora", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:190:035385

Metadata
TitleAkustičko modeliranje govora za potrebe sinteze govora
Title (english)Acoustic modelling for speech synthesis
AuthorToni Polonijo
MentorIvo Ipšić (mentor)
Committee memberJonatan Lerga (predsjednik povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
Committee memberIvo Ipšić (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Intelligent Computing Systems)
Rijeka
Defense date and country2020-05-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Architecture of Computer Systems
Abstract
U diplomskom radu opisan je postupak izgradnje akustičkih modela dubokim neuronskim mrežama za sintezu govora. Testirane su dvije arhitekture izgrađene unaprijednim neuronskim mrežama te četiri arhitekture gdje su korištene mreže s povratnim vezama uz LSTM ćelije. Akustički modeli gdje su korištene mreže s povratnim vezama postigle su bolje objektivne i subjektivne rezultate nego modeli učeni unaprijednim neuronskim mrežama.
Abstract (english)
In this master thesis, different acoustic models using deep neural networks are built for the purposes of speech synthesis. Two acoustic models were built and tested using feed-forward neural networks, and four acoustic models were built and tested using recurrent neural networks with LSTM cells. Acoustic models built with recurrent neural networks yielded better results than models built with feed-forward neural networks.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:035385
Study programmeTitle: Computer Engineering
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 conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-08-24 12:44:58