Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377079685> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4377079685 endingPage "597" @default.
- W4377079685 startingPage "593" @default.
- W4377079685 abstract "This letter proposes an effective speaker-conditioning method that is applicable to zero-shot multi-speaker text-to-speech (ZSM-TTS) systems. Based on the inductive bias in the speech generation task, in which local context information in text/phoneme sequences heavily affect the speaker characteristics of the output speech, we propose a Speaker-Conditional Convolutional Neural Network (SC-CNN) for the ZSM-TTS task. SC-CNN first predicts convolutional kernels from each learned speaker embedding, then applies 1-D convolutions to phoneme sequences with the predicted kernels. It utilizes the aforementioned inductive bias and effectively models the characteristic of speech by providing the speaker-specific local context in phonetic domain. We also build both FastSpeech2 and VITS-based ZSM-TTS systems to verify its superiority over conventional speaker conditioning methods. The results confirm that the models with SC-CNN outperform the recent ZSM-TTS models in terms of both subjective and objective measurements." @default.
- W4377079685 created "2023-05-20" @default.
- W4377079685 creator A5022768647 @default.
- W4377079685 creator A5032657615 @default.
- W4377079685 creator A5056128107 @default.
- W4377079685 creator A5074612173 @default.
- W4377079685 creator A5085480169 @default.
- W4377079685 date "2023-01-01" @default.
- W4377079685 modified "2023-10-16" @default.
- W4377079685 title "SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems" @default.
- W4377079685 cites W2531409750 @default.
- W4377079685 cites W2903739847 @default.
- W4377079685 cites W2964243274 @default.
- W4377079685 cites W2972359262 @default.
- W4377079685 cites W2998572311 @default.
- W4377079685 cites W3015645837 @default.
- W4377079685 cites W3016159759 @default.
- W4377079685 cites W3024869864 @default.
- W4377079685 cites W3095199334 @default.
- W4377079685 cites W3095545636 @default.
- W4377079685 cites W3097777922 @default.
- W4377079685 cites W3161704465 @default.
- W4377079685 cites W4221166168 @default.
- W4377079685 cites W4225746985 @default.
- W4377079685 cites W4313148337 @default.
- W4377079685 doi "https://doi.org/10.1109/lsp.2023.3277786" @default.
- W4377079685 hasPublicationYear "2023" @default.
- W4377079685 type Work @default.
- W4377079685 citedByCount "0" @default.
- W4377079685 crossrefType "journal-article" @default.
- W4377079685 hasAuthorship W4377079685A5022768647 @default.
- W4377079685 hasAuthorship W4377079685A5032657615 @default.
- W4377079685 hasAuthorship W4377079685A5056128107 @default.
- W4377079685 hasAuthorship W4377079685A5074612173 @default.
- W4377079685 hasAuthorship W4377079685A5085480169 @default.
- W4377079685 hasConcept C133892786 @default.
- W4377079685 hasConcept C149838564 @default.
- W4377079685 hasConcept C151730666 @default.
- W4377079685 hasConcept C153180895 @default.
- W4377079685 hasConcept C154945302 @default.
- W4377079685 hasConcept C2779343474 @default.
- W4377079685 hasConcept C28490314 @default.
- W4377079685 hasConcept C41008148 @default.
- W4377079685 hasConcept C81363708 @default.
- W4377079685 hasConcept C86803240 @default.
- W4377079685 hasConceptScore W4377079685C133892786 @default.
- W4377079685 hasConceptScore W4377079685C149838564 @default.
- W4377079685 hasConceptScore W4377079685C151730666 @default.
- W4377079685 hasConceptScore W4377079685C153180895 @default.
- W4377079685 hasConceptScore W4377079685C154945302 @default.
- W4377079685 hasConceptScore W4377079685C2779343474 @default.
- W4377079685 hasConceptScore W4377079685C28490314 @default.
- W4377079685 hasConceptScore W4377079685C41008148 @default.
- W4377079685 hasConceptScore W4377079685C81363708 @default.
- W4377079685 hasConceptScore W4377079685C86803240 @default.
- W4377079685 hasLocation W43770796851 @default.
- W4377079685 hasOpenAccess W4377079685 @default.
- W4377079685 hasPrimaryLocation W43770796851 @default.
- W4377079685 hasRelatedWork W1509309911 @default.
- W4377079685 hasRelatedWork W1521049138 @default.
- W4377079685 hasRelatedWork W2144208207 @default.
- W4377079685 hasRelatedWork W2162158162 @default.
- W4377079685 hasRelatedWork W3091785813 @default.
- W4377079685 hasRelatedWork W3093612317 @default.
- W4377079685 hasRelatedWork W3205435834 @default.
- W4377079685 hasRelatedWork W4214739189 @default.
- W4377079685 hasRelatedWork W4368276095 @default.
- W4377079685 hasRelatedWork W2175373321 @default.
- W4377079685 hasVolume "30" @default.
- W4377079685 isParatext "false" @default.
- W4377079685 isRetracted "false" @default.
- W4377079685 workType "article" @default.