Matches in SemOpenAlex for { <https://semopenalex.org/work/W3146962208> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3146962208 abstract "Singing voice synthesis has been paid rising attention with the rapid development of speech synthesis area. In general, a studio-level singing corpus is usually necessary to produce a natural singing voice from lyrics and music-related transcription. However, such a corpus is difficult to collect since it's hard for many of us to sing like a professional singer. In this paper, we propose an approach - Learn2Sing that only needs a singing teacher to generate the target speakers' singing voice without their singing voice data. In our approach, a teacher's singing corpus and speech from multiple target speakers are trained in a frame-level auto-regressive acoustic model where singing and speaking share the common speaker embedding and style tag embedding. Meanwhile, since there is no music-related transcription for the target speaker, we use log-scale fundamental frequency (LF0) as an auxiliary feature as the inputs of the acoustic model for building a unified input representation. In order to enable the target speaker to sing without singing reference audio in the inference stage, a duration model and an LF0 prediction model are also trained. Particularly, we employ domain adversarial training (DAT) in the acoustic model, which aims to enhance the singing performance of target speakers by disentangling style from acoustic features of singing and speaking data. Our experiments indicate that the proposed approach is capable of synthesizing singing voice for target speaker given only their speech samples." @default.
- W3146962208 created "2021-04-13" @default.
- W3146962208 creator A5013928267 @default.
- W3146962208 creator A5024077352 @default.
- W3146962208 creator A5049459342 @default.
- W3146962208 creator A5064426059 @default.
- W3146962208 creator A5066245750 @default.
- W3146962208 date "2021-01-19" @default.
- W3146962208 modified "2023-09-27" @default.
- W3146962208 title "Learn2Sing: Target Speaker Singing Voice Synthesis by Learning from a Singing Teacher" @default.
- W3146962208 cites W2402539796 @default.
- W3146962208 cites W2515336442 @default.
- W3146962208 cites W2889244839 @default.
- W3146962208 cites W2921576841 @default.
- W3146962208 cites W2963568710 @default.
- W3146962208 cites W2964243274 @default.
- W3146962208 cites W3142087749 @default.
- W3146962208 doi "https://doi.org/10.1109/slt48900.2021.9383585" @default.
- W3146962208 hasPublicationYear "2021" @default.
- W3146962208 type Work @default.
- W3146962208 sameAs 3146962208 @default.
- W3146962208 citedByCount "3" @default.
- W3146962208 countsByYear W31469622082021 @default.
- W3146962208 countsByYear W31469622082022 @default.
- W3146962208 crossrefType "proceedings-article" @default.
- W3146962208 hasAuthorship W3146962208A5013928267 @default.
- W3146962208 hasAuthorship W3146962208A5024077352 @default.
- W3146962208 hasAuthorship W3146962208A5049459342 @default.
- W3146962208 hasAuthorship W3146962208A5064426059 @default.
- W3146962208 hasAuthorship W3146962208A5066245750 @default.
- W3146962208 hasBestOaLocation W31469622082 @default.
- W3146962208 hasConcept C121332964 @default.
- W3146962208 hasConcept C24890656 @default.
- W3146962208 hasConcept C2776436406 @default.
- W3146962208 hasConcept C28490314 @default.
- W3146962208 hasConcept C41008148 @default.
- W3146962208 hasConcept C44819458 @default.
- W3146962208 hasConceptScore W3146962208C121332964 @default.
- W3146962208 hasConceptScore W3146962208C24890656 @default.
- W3146962208 hasConceptScore W3146962208C2776436406 @default.
- W3146962208 hasConceptScore W3146962208C28490314 @default.
- W3146962208 hasConceptScore W3146962208C41008148 @default.
- W3146962208 hasConceptScore W3146962208C44819458 @default.
- W3146962208 hasLocation W31469622081 @default.
- W3146962208 hasLocation W31469622082 @default.
- W3146962208 hasOpenAccess W3146962208 @default.
- W3146962208 hasPrimaryLocation W31469622081 @default.
- W3146962208 hasRelatedWork W2028766658 @default.
- W3146962208 hasRelatedWork W2057745663 @default.
- W3146962208 hasRelatedWork W2059239154 @default.
- W3146962208 hasRelatedWork W2552590214 @default.
- W3146962208 hasRelatedWork W2736042296 @default.
- W3146962208 hasRelatedWork W2797489470 @default.
- W3146962208 hasRelatedWork W2935701729 @default.
- W3146962208 hasRelatedWork W2945891342 @default.
- W3146962208 hasRelatedWork W2999886366 @default.
- W3146962208 hasRelatedWork W3207249698 @default.
- W3146962208 isParatext "false" @default.
- W3146962208 isRetracted "false" @default.
- W3146962208 magId "3146962208" @default.
- W3146962208 workType "article" @default.