Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225329057> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4225329057 abstract "Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study, we investigate zero-shot VC from a novel perspective of self-supervised disentangled speech representation learning. Specifically, we achieve the disentanglement by balancing the information flow between global speaker representation and time-varying content representation in a sequential variational autoencoder (VAE). A zero-shot voice conversion is performed by feeding an arbitrary speaker embedding and content embeddings to the VAE decoder. Besides that, an on-the-fly data augmentation training strategy is applied to make the learned representation noise invariant. On TIMIT and VCTK datasets, we achieve state-of-the-art performance on both objective evaluation, i.e., speaker verification (SV) on speaker embedding and content embedding, and subjective evaluation, i.e., voice naturalness and similarity, and remains to be robust even with noisy source/target utterances." @default.
- W4225329057 created "2022-05-05" @default.
- W4225329057 creator A5034476404 @default.
- W4225329057 creator A5038985725 @default.
- W4225329057 creator A5088059015 @default.
- W4225329057 date "2022-05-23" @default.
- W4225329057 modified "2023-09-30" @default.
- W4225329057 title "Robust Disentangled Variational Speech Representation Learning for Zero-Shot Voice Conversion" @default.
- W4225329057 cites W2120605154 @default.
- W4225329057 cites W2120847449 @default.
- W4225329057 cites W2156142001 @default.
- W4225329057 cites W2806503584 @default.
- W4225329057 cites W2902070858 @default.
- W4225329057 cites W2963539064 @default.
- W4225329057 cites W2972659941 @default.
- W4225329057 cites W3034603995 @default.
- W4225329057 cites W3097152652 @default.
- W4225329057 cites W3099078140 @default.
- W4225329057 cites W3154451338 @default.
- W4225329057 doi "https://doi.org/10.1109/icassp43922.2022.9747272" @default.
- W4225329057 hasPublicationYear "2022" @default.
- W4225329057 type Work @default.
- W4225329057 citedByCount "7" @default.
- W4225329057 countsByYear W42253290572023 @default.
- W4225329057 crossrefType "proceedings-article" @default.
- W4225329057 hasAuthorship W4225329057A5034476404 @default.
- W4225329057 hasAuthorship W4225329057A5038985725 @default.
- W4225329057 hasAuthorship W4225329057A5088059015 @default.
- W4225329057 hasBestOaLocation W42253290572 @default.
- W4225329057 hasConcept C101738243 @default.
- W4225329057 hasConcept C108583219 @default.
- W4225329057 hasConcept C121332964 @default.
- W4225329057 hasConcept C134537474 @default.
- W4225329057 hasConcept C153180895 @default.
- W4225329057 hasConcept C154945302 @default.
- W4225329057 hasConcept C17744445 @default.
- W4225329057 hasConcept C199539241 @default.
- W4225329057 hasConcept C23224414 @default.
- W4225329057 hasConcept C2776359362 @default.
- W4225329057 hasConcept C2778724510 @default.
- W4225329057 hasConcept C28490314 @default.
- W4225329057 hasConcept C41008148 @default.
- W4225329057 hasConcept C41608201 @default.
- W4225329057 hasConcept C62520636 @default.
- W4225329057 hasConcept C94625758 @default.
- W4225329057 hasConceptScore W4225329057C101738243 @default.
- W4225329057 hasConceptScore W4225329057C108583219 @default.
- W4225329057 hasConceptScore W4225329057C121332964 @default.
- W4225329057 hasConceptScore W4225329057C134537474 @default.
- W4225329057 hasConceptScore W4225329057C153180895 @default.
- W4225329057 hasConceptScore W4225329057C154945302 @default.
- W4225329057 hasConceptScore W4225329057C17744445 @default.
- W4225329057 hasConceptScore W4225329057C199539241 @default.
- W4225329057 hasConceptScore W4225329057C23224414 @default.
- W4225329057 hasConceptScore W4225329057C2776359362 @default.
- W4225329057 hasConceptScore W4225329057C2778724510 @default.
- W4225329057 hasConceptScore W4225329057C28490314 @default.
- W4225329057 hasConceptScore W4225329057C41008148 @default.
- W4225329057 hasConceptScore W4225329057C41608201 @default.
- W4225329057 hasConceptScore W4225329057C62520636 @default.
- W4225329057 hasConceptScore W4225329057C94625758 @default.
- W4225329057 hasLocation W42253290571 @default.
- W4225329057 hasLocation W42253290572 @default.
- W4225329057 hasLocation W42253290573 @default.
- W4225329057 hasOpenAccess W4225329057 @default.
- W4225329057 hasPrimaryLocation W42253290571 @default.
- W4225329057 hasRelatedWork W2292254049 @default.
- W4225329057 hasRelatedWork W2335364074 @default.
- W4225329057 hasRelatedWork W2592385986 @default.
- W4225329057 hasRelatedWork W2772780115 @default.
- W4225329057 hasRelatedWork W2897995864 @default.
- W4225329057 hasRelatedWork W2998168123 @default.
- W4225329057 hasRelatedWork W3099179464 @default.
- W4225329057 hasRelatedWork W4281924768 @default.
- W4225329057 hasRelatedWork W4287995534 @default.
- W4225329057 hasRelatedWork W4300480195 @default.
- W4225329057 isParatext "false" @default.
- W4225329057 isRetracted "false" @default.
- W4225329057 workType "article" @default.