Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308170756> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4308170756 abstract "Generating natural speech with a diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the generated speech is still very limited and far from what can be achieved by humans. This is largely due to the use of uni-modal distribution, such as single Gaussian, in the prior works of phone-level prosody modelling. In this work, we propose a novel approach that models phone-level prosodies with a GMM-based mixture density network(MDN) and then extend it for multi-speaker TTS using speaker adaptation transforms of Gaussian means and variances. Furthermore, we show that we can clone the prosodies from a reference speech by sampling prosodies from the Gaussian components that produce the reference prosodies. Our experiments on LJSpeech and LibriTTS dataset show that the proposed method with GMM-based MDN not only achieves significantly better diversity than using a single Gaussian in both single-speaker and multi-speaker TTS, but also provides better naturalness. The prosody cloning experiments demonstrate that the prosody similarity of the proposed method with GMM-based MDN is comparable to recent proposed fine-grained VAE while the target speaker similarity is better." @default.
- W4308170756 created "2022-11-08" @default.
- W4308170756 creator A5035532752 @default.
- W4308170756 creator A5077804071 @default.
- W4308170756 date "2021-05-27" @default.
- W4308170756 modified "2023-10-05" @default.
- W4308170756 title "Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis" @default.
- W4308170756 doi "https://doi.org/10.48550/arxiv.2105.13086" @default.
- W4308170756 hasPublicationYear "2021" @default.
- W4308170756 type Work @default.
- W4308170756 citedByCount "0" @default.
- W4308170756 crossrefType "posted-content" @default.
- W4308170756 hasAuthorship W4308170756A5035532752 @default.
- W4308170756 hasAuthorship W4308170756A5077804071 @default.
- W4308170756 hasBestOaLocation W43081707561 @default.
- W4308170756 hasConcept C103278499 @default.
- W4308170756 hasConcept C115961682 @default.
- W4308170756 hasConcept C121332964 @default.
- W4308170756 hasConcept C134537474 @default.
- W4308170756 hasConcept C138885662 @default.
- W4308170756 hasConcept C140779682 @default.
- W4308170756 hasConcept C154945302 @default.
- W4308170756 hasConcept C163716315 @default.
- W4308170756 hasConcept C2778707766 @default.
- W4308170756 hasConcept C28490314 @default.
- W4308170756 hasConcept C41008148 @default.
- W4308170756 hasConcept C41895202 @default.
- W4308170756 hasConcept C542774811 @default.
- W4308170756 hasConcept C61224824 @default.
- W4308170756 hasConcept C62520636 @default.
- W4308170756 hasConcept C76155785 @default.
- W4308170756 hasConcept C94915269 @default.
- W4308170756 hasConceptScore W4308170756C103278499 @default.
- W4308170756 hasConceptScore W4308170756C115961682 @default.
- W4308170756 hasConceptScore W4308170756C121332964 @default.
- W4308170756 hasConceptScore W4308170756C134537474 @default.
- W4308170756 hasConceptScore W4308170756C138885662 @default.
- W4308170756 hasConceptScore W4308170756C140779682 @default.
- W4308170756 hasConceptScore W4308170756C154945302 @default.
- W4308170756 hasConceptScore W4308170756C163716315 @default.
- W4308170756 hasConceptScore W4308170756C2778707766 @default.
- W4308170756 hasConceptScore W4308170756C28490314 @default.
- W4308170756 hasConceptScore W4308170756C41008148 @default.
- W4308170756 hasConceptScore W4308170756C41895202 @default.
- W4308170756 hasConceptScore W4308170756C542774811 @default.
- W4308170756 hasConceptScore W4308170756C61224824 @default.
- W4308170756 hasConceptScore W4308170756C62520636 @default.
- W4308170756 hasConceptScore W4308170756C76155785 @default.
- W4308170756 hasConceptScore W4308170756C94915269 @default.
- W4308170756 hasLocation W43081707561 @default.
- W4308170756 hasOpenAccess W4308170756 @default.
- W4308170756 hasPrimaryLocation W43081707561 @default.
- W4308170756 hasRelatedWork W1554502231 @default.
- W4308170756 hasRelatedWork W172797710 @default.
- W4308170756 hasRelatedWork W2029561777 @default.
- W4308170756 hasRelatedWork W2945105049 @default.
- W4308170756 hasRelatedWork W2948317131 @default.
- W4308170756 hasRelatedWork W3100825170 @default.
- W4308170756 hasRelatedWork W3134835907 @default.
- W4308170756 hasRelatedWork W3165080709 @default.
- W4308170756 hasRelatedWork W4288365855 @default.
- W4308170756 hasRelatedWork W4387098302 @default.
- W4308170756 isParatext "false" @default.
- W4308170756 isRetracted "false" @default.
- W4308170756 workType "article" @default.