Show simple item record

The Development of Phone Duration Model in Speech Synthesis in theSerbian Language

dc.contributor.advisorDelić, Vlado
dc.contributor.otherHadžić, Olga
dc.contributor.otherBajić, Dragana
dc.contributor.otherJovičić, Slobodan
dc.contributor.otherMarković, Maja
dc.contributor.otherDelić, Vlado
dc.creatorSovilj-Nikić, Sandra
dc.date.accessioned2020-06-23T13:30:45Z
dc.date.available2020-06-23T13:30:45Z
dc.date.available2020-07-03T14:16:22Z
dc.date.issued2014-07-10
dc.identifier.urihttps://www.cris.uns.ac.rs/DownloadFileServlet/Disertacija139661812811285.pdf?controlNumber=(BISIS)85851&fileName=139661812811285.pdf&id=1738&source=NaRDuS&language=srsr
dc.identifier.urihttp://nardus.mpn.gov.rs/handle/123456789/12359
dc.identifier.urihttps://www.cris.uns.ac.rs/record.jsf?recordId=85851&source=NaRDuS&language=srsr
dc.identifier.urihttps://www.cris.uns.ac.rs/DownloadFileServlet/IzvestajKomisije139661818165942.pdf?controlNumber=(BISIS)85851&fileName=139661818165942.pdf&id=1739&source=NaRDuS&language=srsr
dc.description.abstractU okviru ove disertacije razvijeno je više različitih modela trajanja glasova u srpskom jeziku primenom odgovarajućih metoda automatskog učenja. Izvršena je objektivna evaluacija razvijenih modela i njihovo međusobno poređenje na osnovu kvantitativnih pokazatelja kao što su RMSE(engl. root-mean-squared error), MAE (engl. mean absolute error) i CC (engl. correlation coefficient). Takođe je izvršeno poređenje modela za srpski jezik sa performansama modela razvijenih za druge jezike, pri čemu je uočeno da su performanse modela razvijenih u ovoj disertaciji uporedljive ili čak prevazilaze performanse modela koji su razvijeni za druge jezike.sr
dc.description.abstractIn this dissertation several different phone duration models of the Serbain language using appropriate machine learning algorithms were developed. The objective evaluation of the models obtained and their mutual comparison based on quantitative measures such as RMSE (root-mean-squared error), MAE (mean absolute error) and CC (correlation coefficient) were performed. The comparison of the models developed for the Serbian language with the performances of the models developed for other languages is also carried out. It was observed that the performances of the models developed in this dissertation are comparable or even outperform the performances of the models that have been developed for other languages.en
dc.languagesr (latin script)
dc.publisherУниверзитет у Новом Саду, Факултет техничких наукаsr
dc.rightsopenAccessen
dc.sourceУниверзитет у Новом Садуsr
dc.subjectSinteza govora, modelovanje trajanja glasova, metode automatskog učenjasr
dc.subjectSpeech synthesis, phone duration modeling, machine learning algorithmsUCen
dc.titleRazvoj matematičkog modela trajanja glasova u automatskoj sintezi govora na srpskom jezikusr
dc.title.alternativeThe Development of Phone Duration Model in Speech Synthesis in theSerbian Languageen
dc.typedoctoralThesissr
dc.rights.licenseCC0
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/44268/Disertacija.pdf
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/44269/IzvestajKomisije.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record