FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382935141> ?p ?o ?g. }

• W4382935141 abstract "Speech synthesis quality prediction has made remarkable progress with the development of supervised and self-supervised learning (SSL) MOS predictors but some aspects related to the data are still unclear and require further study. In this paper, we evaluate several MOS predictors based on wav2vec 2.0 and the NISQA speech quality prediction model to explore the role of the training data, the influence of the system type, and the role of cross-domain features in SSL models. Our evaluation is based on the VoiceMOS challenge dataset. Results show that SSL-based models show the highest correlation and lowest mean squared error compared to supervised models. The key point of this study is that benchmarking the statistical performance of MOS predictors alone is not sufficient to rank models since potential issues hidden in the data could bias the evaluated performances." @default.
• W4382935141 created "2023-07-04" @default.
• W4382935141 creator A5001022750 @default.
• W4382935141 creator A5008608844 @default.
• W4382935141 creator A5014946755 @default.
• W4382935141 creator A5016309279 @default.
• W4382935141 creator A5070792118 @default.
• W4382935141 creator A5084672392 @default.
• W4382935141 creator A5091296882 @default.
• W4382935141 date "2023-06-13" @default.
• W4382935141 modified "2023-09-24" @default.
• W4382935141 title "A Comparison Of Deep Learning MOS Predictors For Speech Synthesis Quality" @default.
• W4382935141 cites W1494198834 @default.
• W4382935141 cites W2069355054 @default.
• W4382935141 cites W2561217444 @default.
• W4382935141 cites W2972394484 @default.
• W4382935141 cites W2976159681 @default.
• W4382935141 cites W2985767095 @default.
• W4382935141 cites W3095087462 @default.
• W4382935141 cites W3098557217 @default.
• W4382935141 cites W3175537473 @default.
• W4382935141 cites W3196225973 @default.
• W4382935141 cites W3196475561 @default.
• W4382935141 cites W3202278141 @default.
• W4382935141 cites W3207924272 @default.
• W4382935141 cites W3207932315 @default.
• W4382935141 cites W4296068818 @default.
• W4382935141 doi "https://doi.org/10.1109/issc59246.2023.10162088" @default.
• W4382935141 hasPublicationYear "2023" @default.
• W4382935141 type Work @default.
• W4382935141 citedByCount "1" @default.
• W4382935141 countsByYear W43829351412023 @default.
• W4382935141 crossrefType "proceedings-article" @default.
• W4382935141 hasAuthorship W4382935141A5001022750 @default.
• W4382935141 hasAuthorship W4382935141A5008608844 @default.
• W4382935141 hasAuthorship W4382935141A5014946755 @default.
• W4382935141 hasAuthorship W4382935141A5016309279 @default.
• W4382935141 hasAuthorship W4382935141A5070792118 @default.
• W4382935141 hasAuthorship W4382935141A5084672392 @default.
• W4382935141 hasAuthorship W4382935141A5091296882 @default.
• W4382935141 hasBestOaLocation W43829351412 @default.
• W4382935141 hasConcept C105795698 @default.
• W4382935141 hasConcept C108583219 @default.
• W4382935141 hasConcept C111472728 @default.
• W4382935141 hasConcept C117220453 @default.
• W4382935141 hasConcept C119857082 @default.
• W4382935141 hasConcept C127413603 @default.
• W4382935141 hasConcept C138885662 @default.
• W4382935141 hasConcept C139945424 @default.
• W4382935141 hasConcept C144133560 @default.
• W4382935141 hasConcept C154945302 @default.
• W4382935141 hasConcept C162853370 @default.
• W4382935141 hasConcept C176217482 @default.
• W4382935141 hasConcept C21547014 @default.
• W4382935141 hasConcept C2524010 @default.
• W4382935141 hasConcept C26517878 @default.
• W4382935141 hasConcept C2779530757 @default.
• W4382935141 hasConcept C28490314 @default.
• W4382935141 hasConcept C33923547 @default.
• W4382935141 hasConcept C38652104 @default.
• W4382935141 hasConcept C41008148 @default.
• W4382935141 hasConcept C45804977 @default.
• W4382935141 hasConcept C62897895 @default.
• W4382935141 hasConcept C67186912 @default.
• W4382935141 hasConcept C77088390 @default.
• W4382935141 hasConcept C86251818 @default.
• W4382935141 hasConceptScore W4382935141C105795698 @default.
• W4382935141 hasConceptScore W4382935141C108583219 @default.
• W4382935141 hasConceptScore W4382935141C111472728 @default.
• W4382935141 hasConceptScore W4382935141C117220453 @default.
• W4382935141 hasConceptScore W4382935141C119857082 @default.
• W4382935141 hasConceptScore W4382935141C127413603 @default.
• W4382935141 hasConceptScore W4382935141C138885662 @default.
• W4382935141 hasConceptScore W4382935141C139945424 @default.
• W4382935141 hasConceptScore W4382935141C144133560 @default.
• W4382935141 hasConceptScore W4382935141C154945302 @default.
• W4382935141 hasConceptScore W4382935141C162853370 @default.
• W4382935141 hasConceptScore W4382935141C176217482 @default.
• W4382935141 hasConceptScore W4382935141C21547014 @default.
• W4382935141 hasConceptScore W4382935141C2524010 @default.
• W4382935141 hasConceptScore W4382935141C26517878 @default.
• W4382935141 hasConceptScore W4382935141C2779530757 @default.
• W4382935141 hasConceptScore W4382935141C28490314 @default.
• W4382935141 hasConceptScore W4382935141C33923547 @default.
• W4382935141 hasConceptScore W4382935141C38652104 @default.
• W4382935141 hasConceptScore W4382935141C41008148 @default.
• W4382935141 hasConceptScore W4382935141C45804977 @default.
• W4382935141 hasConceptScore W4382935141C62897895 @default.
• W4382935141 hasConceptScore W4382935141C67186912 @default.
• W4382935141 hasConceptScore W4382935141C77088390 @default.
• W4382935141 hasConceptScore W4382935141C86251818 @default.
• W4382935141 hasFunder F4320320847 @default.
• W4382935141 hasLocation W43829351411 @default.
• W4382935141 hasLocation W43829351412 @default.
• W4382935141 hasLocation W43829351413 @default.
• W4382935141 hasOpenAccess W4382935141 @default.
• W4382935141 hasPrimaryLocation W43829351411 @default.
• W4382935141 hasRelatedWork W2765476116 @default.
• W4382935141 hasRelatedWork W2806031239 @default.
• W4382935141 hasRelatedWork W3014300295 @default.

• next