Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375869015> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4375869015 abstract "In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content, speaker characteristics, and speaking style. To disentangle content and speaker representations, we propose a training strategy based on Siamese networks that encourages similarity between the content representations of the original and pitch-shifted audio. Next, we develop a synthesis model with pitch and duration predictors that can effectively reconstruct the speech signal from its decomposed representation. Our framework allows controllable and speaker-adaptive synthesis to perform zero-shot any-to-any voice conversion achieving state-of-the-art results on metrics evaluating speaker similarity, intelligibility, and naturalness. Using just 10 seconds of data for a target speaker, our framework can perform voice swapping and achieves a speaker verification EER of 5.5% for seen speakers and 8.4% for unseen speakers. <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup>" @default.
- W4375869015 created "2023-05-10" @default.
- W4375869015 creator A5015232966 @default.
- W4375869015 creator A5030710635 @default.
- W4375869015 creator A5032957280 @default.
- W4375869015 creator A5036658158 @default.
- W4375869015 creator A5080235829 @default.
- W4375869015 date "2023-06-04" @default.
- W4375869015 modified "2023-09-30" @default.
- W4375869015 title "ACE-VC: Adaptive and Controllable Voice Conversion Using Explicitly Disentangled Self-Supervised Speech Representations" @default.
- W4375869015 cites W10800834 @default.
- W4375869015 cites W1494198834 @default.
- W4375869015 cites W2091425152 @default.
- W4375869015 cites W2127141656 @default.
- W4375869015 cites W2518172956 @default.
- W4375869015 cites W2576309025 @default.
- W4375869015 cites W2806000759 @default.
- W4375869015 cites W2963466847 @default.
- W4375869015 cites W2972659941 @default.
- W4375869015 cites W2981087920 @default.
- W4375869015 cites W3015537910 @default.
- W4375869015 cites W3097777922 @default.
- W4375869015 cites W3161627112 @default.
- W4375869015 cites W3198095523 @default.
- W4375869015 cites W3207300132 @default.
- W4375869015 doi "https://doi.org/10.1109/icassp49357.2023.10094850" @default.
- W4375869015 hasPublicationYear "2023" @default.
- W4375869015 type Work @default.
- W4375869015 citedByCount "1" @default.
- W4375869015 countsByYear W43758690152023 @default.
- W4375869015 crossrefType "proceedings-article" @default.
- W4375869015 hasAuthorship W4375869015A5015232966 @default.
- W4375869015 hasAuthorship W4375869015A5030710635 @default.
- W4375869015 hasAuthorship W4375869015A5032957280 @default.
- W4375869015 hasAuthorship W4375869015A5036658158 @default.
- W4375869015 hasAuthorship W4375869015A5080235829 @default.
- W4375869015 hasBestOaLocation W43758690151 @default.
- W4375869015 hasConcept C103278499 @default.
- W4375869015 hasConcept C111472728 @default.
- W4375869015 hasConcept C115961682 @default.
- W4375869015 hasConcept C121332964 @default.
- W4375869015 hasConcept C133892786 @default.
- W4375869015 hasConcept C134537474 @default.
- W4375869015 hasConcept C138885662 @default.
- W4375869015 hasConcept C14999030 @default.
- W4375869015 hasConcept C154945302 @default.
- W4375869015 hasConcept C204321447 @default.
- W4375869015 hasConcept C2775852435 @default.
- W4375869015 hasConcept C28490314 @default.
- W4375869015 hasConcept C41008148 @default.
- W4375869015 hasConcept C60048801 @default.
- W4375869015 hasConcept C61328038 @default.
- W4375869015 hasConcept C62520636 @default.
- W4375869015 hasConceptScore W4375869015C103278499 @default.
- W4375869015 hasConceptScore W4375869015C111472728 @default.
- W4375869015 hasConceptScore W4375869015C115961682 @default.
- W4375869015 hasConceptScore W4375869015C121332964 @default.
- W4375869015 hasConceptScore W4375869015C133892786 @default.
- W4375869015 hasConceptScore W4375869015C134537474 @default.
- W4375869015 hasConceptScore W4375869015C138885662 @default.
- W4375869015 hasConceptScore W4375869015C14999030 @default.
- W4375869015 hasConceptScore W4375869015C154945302 @default.
- W4375869015 hasConceptScore W4375869015C204321447 @default.
- W4375869015 hasConceptScore W4375869015C2775852435 @default.
- W4375869015 hasConceptScore W4375869015C28490314 @default.
- W4375869015 hasConceptScore W4375869015C41008148 @default.
- W4375869015 hasConceptScore W4375869015C60048801 @default.
- W4375869015 hasConceptScore W4375869015C61328038 @default.
- W4375869015 hasConceptScore W4375869015C62520636 @default.
- W4375869015 hasLocation W43758690151 @default.
- W4375869015 hasLocation W43758690152 @default.
- W4375869015 hasOpenAccess W4375869015 @default.
- W4375869015 hasPrimaryLocation W43758690151 @default.
- W4375869015 hasRelatedWork W1540787848 @default.
- W4375869015 hasRelatedWork W1572861854 @default.
- W4375869015 hasRelatedWork W1677284209 @default.
- W4375869015 hasRelatedWork W2109051065 @default.
- W4375869015 hasRelatedWork W2120260381 @default.
- W4375869015 hasRelatedWork W2394527820 @default.
- W4375869015 hasRelatedWork W3210530853 @default.
- W4375869015 hasRelatedWork W4210590938 @default.
- W4375869015 hasRelatedWork W4375869015 @default.
- W4375869015 hasRelatedWork W4386302780 @default.
- W4375869015 isParatext "false" @default.
- W4375869015 isRetracted "false" @default.
- W4375869015 workType "article" @default.