000007478 001__ 7478
000007478 005__ 20231129124940.0
000007478 0247_ $$2DOI$$a10.6083/z316q221w
000007478 037__ $$aETD
000007478 245__ $$aSpeech representation learning for voice conversion
000007478 260__ $$bOregon Health and Science University
000007478 269__ $$a2019
000007478 336__ $$aDissertation
000007478 502__ $$bPh.D.
000007478 520__ $$aThe sound of a person's voice is an important factor in human communication. VoiceConversion (VC) is a technology that modifies a source speaker's speech utterance to sound as if it has been spoken by a target speaker. VC o?ers a number of useful applications. For example, personalizing a text-to-speech system to speak with a new voice with minimal amount of data, or mimicking the voice of another individual when dubbing a movie in another language. In this dissertation, we consider new approaches in the design of VC systems. We propose techniques for learning speech representations with some characteristics that facilitate building systems for VC.
000007478 542__ $$fIn copyright - single owner
000007478 650__ $$aMachine Learning$$011449
000007478 650__ $$aDeep Learning$$012734
000007478 6531_ $$arepresentation learning
000007478 6531_ $$aautoencoder
000007478 6531_ $$avoice conversion
000007478 6531_ $$avoice transformation
000007478 691__ $$aSchool of Medicine$$041369
000007478 692__ $$aDepartment of Computer Science and Engineering$$041405
000007478 7001_ $$aMohammadi, Seyed H.
000007478 8564_ $$9346ca6b4-f395-44dc-9416-403edf89e621$$s2320702$$uhttps://digitalcollections.ohsu.edu/record/7478/files/mohammadi.hamidreza.2019.pdf
000007478 905__ $$a/rest/prod/z3/16/q2/21/z316q221w
000007478 909CO $$ooai:digitalcollections.ohsu.edu:7478$$pstudent-work
000007478 980__ $$aTheses and Dissertations