Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308757493> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4308757493 abstract "Voice conversion for highly expressive speech is challenging. Current approaches struggle with the balancing between speaker similarity, intelligibility and expressiveness. To address this problem, we propose Expressive-VC, a novel end-to-end voice conversion framework that leverages advantages from both neural bottleneck feature (BNF) approach and information perturbation approach. Specifically, we use a BNF encoder and a Perturbed-Wav encoder to form a content extractor to learn linguistic and para-linguistic features respectively, where BNFs come from a robust pre-trained ASR model and the perturbed wave becomes speaker-irrelevant after signal perturbation. We further fuse the linguistic and para-linguistic features through an attention mechanism, where speaker-dependent prosody features are adopted as the attention query, which result from a prosody encoder with target speaker embedding and normalized pitch and energy of source speech as input. Finally the decoder consumes the integrated features and the speaker-dependent prosody feature to generate the converted speech. Experiments demonstrate that Expressive-VC is superior to several state-of-the-art systems, achieving both high expressiveness captured from the source speech and high speaker similarity with the target speaker; meanwhile intelligibility is well maintained." @default.
- W4308757493 created "2022-11-15" @default.
- W4308757493 creator A5009337933 @default.
- W4308757493 creator A5015560758 @default.
- W4308757493 creator A5029817092 @default.
- W4308757493 creator A5036369578 @default.
- W4308757493 creator A5049213273 @default.
- W4308757493 creator A5050166453 @default.
- W4308757493 creator A5050219087 @default.
- W4308757493 creator A5081164682 @default.
- W4308757493 date "2022-11-09" @default.
- W4308757493 modified "2023-09-26" @default.
- W4308757493 title "Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features" @default.
- W4308757493 doi "https://doi.org/10.48550/arxiv.2211.04710" @default.
- W4308757493 hasPublicationYear "2022" @default.
- W4308757493 type Work @default.
- W4308757493 citedByCount "0" @default.
- W4308757493 crossrefType "posted-content" @default.
- W4308757493 hasAuthorship W4308757493A5009337933 @default.
- W4308757493 hasAuthorship W4308757493A5015560758 @default.
- W4308757493 hasAuthorship W4308757493A5029817092 @default.
- W4308757493 hasAuthorship W4308757493A5036369578 @default.
- W4308757493 hasAuthorship W4308757493A5049213273 @default.
- W4308757493 hasAuthorship W4308757493A5050166453 @default.
- W4308757493 hasAuthorship W4308757493A5050219087 @default.
- W4308757493 hasAuthorship W4308757493A5081164682 @default.
- W4308757493 hasBestOaLocation W43087574931 @default.
- W4308757493 hasConcept C111472728 @default.
- W4308757493 hasConcept C111919701 @default.
- W4308757493 hasConcept C118505674 @default.
- W4308757493 hasConcept C138885662 @default.
- W4308757493 hasConcept C154945302 @default.
- W4308757493 hasConcept C28490314 @default.
- W4308757493 hasConcept C41008148 @default.
- W4308757493 hasConcept C41608201 @default.
- W4308757493 hasConcept C542774811 @default.
- W4308757493 hasConcept C60048801 @default.
- W4308757493 hasConceptScore W4308757493C111472728 @default.
- W4308757493 hasConceptScore W4308757493C111919701 @default.
- W4308757493 hasConceptScore W4308757493C118505674 @default.
- W4308757493 hasConceptScore W4308757493C138885662 @default.
- W4308757493 hasConceptScore W4308757493C154945302 @default.
- W4308757493 hasConceptScore W4308757493C28490314 @default.
- W4308757493 hasConceptScore W4308757493C41008148 @default.
- W4308757493 hasConceptScore W4308757493C41608201 @default.
- W4308757493 hasConceptScore W4308757493C542774811 @default.
- W4308757493 hasConceptScore W4308757493C60048801 @default.
- W4308757493 hasLocation W43087574931 @default.
- W4308757493 hasLocation W43087574932 @default.
- W4308757493 hasOpenAccess W4308757493 @default.
- W4308757493 hasPrimaryLocation W43087574931 @default.
- W4308757493 hasRelatedWork W2166000452 @default.
- W4308757493 hasRelatedWork W2364970235 @default.
- W4308757493 hasRelatedWork W2928664166 @default.
- W4308757493 hasRelatedWork W2930648092 @default.
- W4308757493 hasRelatedWork W2952917250 @default.
- W4308757493 hasRelatedWork W3015707856 @default.
- W4308757493 hasRelatedWork W3163296124 @default.
- W4308757493 hasRelatedWork W3172289592 @default.
- W4308757493 hasRelatedWork W3196305160 @default.
- W4308757493 hasRelatedWork W4286800517 @default.
- W4308757493 isParatext "false" @default.
- W4308757493 isRetracted "false" @default.
- W4308757493 workType "article" @default.