DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Soonbeom | ko |
dc.contributor.author | KIM, WON IL | ko |
dc.contributor.author | Park, Sae Byul | ko |
dc.contributor.author | Yong, Sangeon | ko |
dc.contributor.author | Nam, Juhan | ko |
dc.date.accessioned | 2020-06-11T01:20:33Z | - |
dc.date.available | 2020-06-11T01:20:33Z | - |
dc.date.created | 2020-06-09 | - |
dc.date.created | 2020-06-09 | - |
dc.date.issued | 2020-05-07 | - |
dc.identifier.citation | 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, pp.7234 - 7238 | - |
dc.identifier.issn | 1520-6149 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274607 | - |
dc.description.abstract | Singing voice synthesis is a generative task that involves not only multidimensional controls of a singer model such as phonetic modulation by lyrics and pitch control by music score but also expressive elements such as breath sounds and vibrato. Recently, end-to-end learning models based on generative adversarial network (GAN) have drawn much interest as it requires less domain-specific processing but provides high sound quality. When GAN is applied to the audio domain, it entails several issues: the choice of audio representation to generate, handling temporal continuity between two adjacent outputs, and finding an effective loss metric for the audio representation. In this paper, we propose a Korean singing voice synthesis system that addresses the issues using an auto-regressive algorithm that generates spectrogram with the boundary equilibrium GAN objective. Through the qualitative test, we show the proposed methods are superior to the original GAN objective and non-auto-regressive model. We also show that our proposed method can render natural expressions such as continuous pitch contours and breath sounds. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Korean Singing Voice Synthesis Based on Auto-Regressive Boundary Equilibrium GAN | - |
dc.type | Conference | - |
dc.identifier.wosid | 000615970407100 | - |
dc.identifier.scopusid | 2-s2.0-85089212626 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 7234 | - |
dc.citation.endingpage | 7238 | - |
dc.citation.publicationname | 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 | - |
dc.identifier.conferencecountry | SP | - |
dc.identifier.conferencelocation | Barcelona | - |
dc.identifier.doi | 10.1109/ICASSP40776.2020.9053950 | - |
dc.contributor.localauthor | Nam, Juhan | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.