Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376123105> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4376123105 abstract "The virtual world is being established in which digital humans are created indistinguishable from real humans. Producing their audio-related capabilities is crucial since voice conveys extensive personal characteristics. We aim to create a controllable audio-form virtual singer; however, supervised modeling and controlling all different factors of the singing voice, such as timbre, tempo, pitch, and lyrics, is extremely difficult since accurately labeling all such information needs enormous labor work. In this paper, we propose a framework that could digitize a person's voice by simply listening to the clean voice recordings of any content in a fully unsupervised manner and predict singing voices even only using speaking recordings. A variational auto-encoder (VAE) based framework is developed, which leverages a set of pre-trained models to encode the audio as various hidden embeddings representing different factors of the singing voice, and further decodes the embeddings into raw audio. By manipulating the hidden embeddings for different factors, the resulting singing voices can be controlled, and new virtual singers can also be further generated by interpolating between timbres. Evaluations of different types of experiments demonstrate the proposed method's effectiveness. The proposed method is the critical technique for producing the AI choir, which empowered the human-AI symbiotic orchestra in Hong Kong in July 2022." @default.
- W4376123105 created "2023-05-12" @default.
- W4376123105 creator A5018386422 @default.
- W4376123105 creator A5040827219 @default.
- W4376123105 creator A5045081171 @default.
- W4376123105 creator A5061082180 @default.
- W4376123105 date "2023-05-09" @default.
- W4376123105 modified "2023-09-27" @default.
- W4376123105 title "Learn to Sing by Listening: Building Controllable Virtual Singer by Unsupervised Learning from Voice Recordings" @default.
- W4376123105 doi "https://doi.org/10.48550/arxiv.2305.05401" @default.
- W4376123105 hasPublicationYear "2023" @default.
- W4376123105 type Work @default.
- W4376123105 citedByCount "0" @default.
- W4376123105 crossrefType "posted-content" @default.
- W4376123105 hasAuthorship W4376123105A5018386422 @default.
- W4376123105 hasAuthorship W4376123105A5040827219 @default.
- W4376123105 hasAuthorship W4376123105A5045081171 @default.
- W4376123105 hasAuthorship W4376123105A5061082180 @default.
- W4376123105 hasBestOaLocation W43761231051 @default.
- W4376123105 hasConcept C121332964 @default.
- W4376123105 hasConcept C13895895 @default.
- W4376123105 hasConcept C142362112 @default.
- W4376123105 hasConcept C153349607 @default.
- W4376123105 hasConcept C15744967 @default.
- W4376123105 hasConcept C177264268 @default.
- W4376123105 hasConcept C177291462 @default.
- W4376123105 hasConcept C199360897 @default.
- W4376123105 hasConcept C20766975 @default.
- W4376123105 hasConcept C24890656 @default.
- W4376123105 hasConcept C2776436406 @default.
- W4376123105 hasConcept C2776539107 @default.
- W4376123105 hasConcept C2779426996 @default.
- W4376123105 hasConcept C28490314 @default.
- W4376123105 hasConcept C31258907 @default.
- W4376123105 hasConcept C41008148 @default.
- W4376123105 hasConcept C44819458 @default.
- W4376123105 hasConcept C46312422 @default.
- W4376123105 hasConcept C558565934 @default.
- W4376123105 hasConcept C64922751 @default.
- W4376123105 hasConcept C87687168 @default.
- W4376123105 hasConceptScore W4376123105C121332964 @default.
- W4376123105 hasConceptScore W4376123105C13895895 @default.
- W4376123105 hasConceptScore W4376123105C142362112 @default.
- W4376123105 hasConceptScore W4376123105C153349607 @default.
- W4376123105 hasConceptScore W4376123105C15744967 @default.
- W4376123105 hasConceptScore W4376123105C177264268 @default.
- W4376123105 hasConceptScore W4376123105C177291462 @default.
- W4376123105 hasConceptScore W4376123105C199360897 @default.
- W4376123105 hasConceptScore W4376123105C20766975 @default.
- W4376123105 hasConceptScore W4376123105C24890656 @default.
- W4376123105 hasConceptScore W4376123105C2776436406 @default.
- W4376123105 hasConceptScore W4376123105C2776539107 @default.
- W4376123105 hasConceptScore W4376123105C2779426996 @default.
- W4376123105 hasConceptScore W4376123105C28490314 @default.
- W4376123105 hasConceptScore W4376123105C31258907 @default.
- W4376123105 hasConceptScore W4376123105C41008148 @default.
- W4376123105 hasConceptScore W4376123105C44819458 @default.
- W4376123105 hasConceptScore W4376123105C46312422 @default.
- W4376123105 hasConceptScore W4376123105C558565934 @default.
- W4376123105 hasConceptScore W4376123105C64922751 @default.
- W4376123105 hasConceptScore W4376123105C87687168 @default.
- W4376123105 hasLocation W43761231051 @default.
- W4376123105 hasOpenAccess W4376123105 @default.
- W4376123105 hasPrimaryLocation W43761231051 @default.
- W4376123105 hasRelatedWork W1568071121 @default.
- W4376123105 hasRelatedWork W2066598518 @default.
- W4376123105 hasRelatedWork W2108382268 @default.
- W4376123105 hasRelatedWork W2109622212 @default.
- W4376123105 hasRelatedWork W2168987487 @default.
- W4376123105 hasRelatedWork W2395416690 @default.
- W4376123105 hasRelatedWork W2562176306 @default.
- W4376123105 hasRelatedWork W2566766850 @default.
- W4376123105 hasRelatedWork W3189847119 @default.
- W4376123105 hasRelatedWork W4312625753 @default.
- W4376123105 isParatext "false" @default.
- W4376123105 isRetracted "false" @default.
- W4376123105 workType "article" @default.