Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862431> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4319862431 abstract "One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity and speech content, a task that still remains challenging. Here, we propose a novel approach to learning disentangled speech representation by transfer learning from style-based text-to-speech (TTS) models. With cycle consistent and adversarial training, the style-based TTS models can perform transcription-guided one-shot VC with high fidelity and similarity. By learning an additional mel-spectrogram encoder through a teacher-student knowledge transfer and novel data augmentation scheme, our approach results in disentangled speech representation without needing the input text. The subjective evaluation shows that our approach can significantly outperform the previous state-of-the-art one-shot voice conversion models in both naturalness and similarity." @default.
- W4319862431 created "2023-02-11" @default.
- W4319862431 creator A5023800090 @default.
- W4319862431 creator A5033351155 @default.
- W4319862431 creator A5070114472 @default.
- W4319862431 date "2023-01-09" @default.
- W4319862431 modified "2023-09-30" @default.
- W4319862431 title "Styletts-VC: One-Shot Voice Conversion by Knowledge Transfer From Style-Based TTS Models" @default.
- W4319862431 cites W2747070883 @default.
- W4319862431 cites W2932319787 @default.
- W4319862431 cites W2962780374 @default.
- W4319862431 cites W2964243274 @default.
- W4319862431 cites W2968984153 @default.
- W4319862431 cites W3015209900 @default.
- W4319862431 cites W3015434413 @default.
- W4319862431 cites W3015645837 @default.
- W4319862431 cites W3096864844 @default.
- W4319862431 cites W3098656025 @default.
- W4319862431 cites W3154451338 @default.
- W4319862431 cites W3163475957 @default.
- W4319862431 cites W3163568691 @default.
- W4319862431 cites W3197659778 @default.
- W4319862431 cites W3197763626 @default.
- W4319862431 cites W4210282084 @default.
- W4319862431 cites W4221141917 @default.
- W4319862431 cites W4225304461 @default.
- W4319862431 doi "https://doi.org/10.1109/slt54892.2023.10022498" @default.
- W4319862431 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37577031" @default.
- W4319862431 hasPublicationYear "2023" @default.
- W4319862431 type Work @default.
- W4319862431 citedByCount "2" @default.
- W4319862431 countsByYear W43198624312023 @default.
- W4319862431 crossrefType "proceedings-article" @default.
- W4319862431 hasAuthorship W4319862431A5023800090 @default.
- W4319862431 hasAuthorship W4319862431A5033351155 @default.
- W4319862431 hasAuthorship W4319862431A5070114472 @default.
- W4319862431 hasBestOaLocation W43198624312 @default.
- W4319862431 hasConcept C103278499 @default.
- W4319862431 hasConcept C111919701 @default.
- W4319862431 hasConcept C115961682 @default.
- W4319862431 hasConcept C118505674 @default.
- W4319862431 hasConcept C121332964 @default.
- W4319862431 hasConcept C133892786 @default.
- W4319862431 hasConcept C134537474 @default.
- W4319862431 hasConcept C138885662 @default.
- W4319862431 hasConcept C149838564 @default.
- W4319862431 hasConcept C154945302 @default.
- W4319862431 hasConcept C179926584 @default.
- W4319862431 hasConcept C28490314 @default.
- W4319862431 hasConcept C41008148 @default.
- W4319862431 hasConcept C41895202 @default.
- W4319862431 hasConcept C45273575 @default.
- W4319862431 hasConcept C62520636 @default.
- W4319862431 hasConceptScore W4319862431C103278499 @default.
- W4319862431 hasConceptScore W4319862431C111919701 @default.
- W4319862431 hasConceptScore W4319862431C115961682 @default.
- W4319862431 hasConceptScore W4319862431C118505674 @default.
- W4319862431 hasConceptScore W4319862431C121332964 @default.
- W4319862431 hasConceptScore W4319862431C133892786 @default.
- W4319862431 hasConceptScore W4319862431C134537474 @default.
- W4319862431 hasConceptScore W4319862431C138885662 @default.
- W4319862431 hasConceptScore W4319862431C149838564 @default.
- W4319862431 hasConceptScore W4319862431C154945302 @default.
- W4319862431 hasConceptScore W4319862431C179926584 @default.
- W4319862431 hasConceptScore W4319862431C28490314 @default.
- W4319862431 hasConceptScore W4319862431C41008148 @default.
- W4319862431 hasConceptScore W4319862431C41895202 @default.
- W4319862431 hasConceptScore W4319862431C45273575 @default.
- W4319862431 hasConceptScore W4319862431C62520636 @default.
- W4319862431 hasLocation W43198624311 @default.
- W4319862431 hasLocation W43198624312 @default.
- W4319862431 hasLocation W43198624313 @default.
- W4319862431 hasOpenAccess W4319862431 @default.
- W4319862431 hasPrimaryLocation W43198624311 @default.
- W4319862431 hasRelatedWork W2030361736 @default.
- W4319862431 hasRelatedWork W2044525818 @default.
- W4319862431 hasRelatedWork W2147551994 @default.
- W4319862431 hasRelatedWork W2405486528 @default.
- W4319862431 hasRelatedWork W2897924318 @default.
- W4319862431 hasRelatedWork W2973062255 @default.
- W4319862431 hasRelatedWork W2982277844 @default.
- W4319862431 hasRelatedWork W3011034465 @default.
- W4319862431 hasRelatedWork W3015826515 @default.
- W4319862431 hasRelatedWork W3169874602 @default.
- W4319862431 isParatext "false" @default.
- W4319862431 isRetracted "false" @default.
- W4319862431 workType "article" @default.