Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089231566> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3089231566 abstract "Recently, deep neural network (DNN) based speech synthesis achieved close to human speech quality and became the state-of-the art in the field of text-to-speech (TTS) synthesis systems. However, a major part of its efficiency comes from the use of large quantity of high-quality speech recordings. When this data is not available, other approaches are still preferred.This paper evaluates the DNN-based postfiltering of the synthesised speech as a means to increase the quality of DNN-based TTS systems trained on very limited speech resources. 20 different systems are compared objectively using the Mel Cepstral Distortion measure. The systems differ in terms of: training data, network architecture, and training method. Out of the 20 initial systems, 7 are evaluated subjectively in listening tests performed for two different speakers. Results show that even when starting from as little as 5 minutes of speech recordings, the postfiltering process improves the quality of the synthetic speech output. So it can, therefore, be used as a training strategy for TTS systems where sufficient high-quality data is not available." @default.
- W3089231566 created "2020-10-01" @default.
- W3089231566 creator A5018126799 @default.
- W3089231566 creator A5023042733 @default.
- W3089231566 creator A5038722127 @default.
- W3089231566 creator A5043037309 @default.
- W3089231566 date "2020-08-01" @default.
- W3089231566 modified "2023-10-18" @default.
- W3089231566 title "An Evaluation of Postfiltering for Deep Learning Based Speech Synthesis with Limited Data" @default.
- W3089231566 cites W1500331947 @default.
- W3089231566 cites W2049036695 @default.
- W3089231566 cites W2107860279 @default.
- W3089231566 cites W2144994235 @default.
- W3089231566 cites W2163925746 @default.
- W3089231566 cites W2254699761 @default.
- W3089231566 cites W2401698713 @default.
- W3089231566 cites W2471520273 @default.
- W3089231566 cites W2473388484 @default.
- W3089231566 cites W2494654097 @default.
- W3089231566 cites W2598638573 @default.
- W3089231566 cites W2666408839 @default.
- W3089231566 cites W2738884019 @default.
- W3089231566 cites W2889009313 @default.
- W3089231566 cites W2889414197 @default.
- W3089231566 cites W2891730843 @default.
- W3089231566 cites W2963609956 @default.
- W3089231566 cites W2964169091 @default.
- W3089231566 doi "https://doi.org/10.1109/is48319.2020.9199932" @default.
- W3089231566 hasPublicationYear "2020" @default.
- W3089231566 type Work @default.
- W3089231566 sameAs 3089231566 @default.
- W3089231566 citedByCount "1" @default.
- W3089231566 countsByYear W30892315662022 @default.
- W3089231566 crossrefType "proceedings-article" @default.
- W3089231566 hasAuthorship W3089231566A5018126799 @default.
- W3089231566 hasAuthorship W3089231566A5023042733 @default.
- W3089231566 hasAuthorship W3089231566A5038722127 @default.
- W3089231566 hasAuthorship W3089231566A5043037309 @default.
- W3089231566 hasConcept C108583219 @default.
- W3089231566 hasConcept C111472728 @default.
- W3089231566 hasConcept C126780896 @default.
- W3089231566 hasConcept C138885662 @default.
- W3089231566 hasConcept C144024400 @default.
- W3089231566 hasConcept C14999030 @default.
- W3089231566 hasConcept C154945302 @default.
- W3089231566 hasConcept C177291462 @default.
- W3089231566 hasConcept C194257627 @default.
- W3089231566 hasConcept C202444582 @default.
- W3089231566 hasConcept C2776257435 @default.
- W3089231566 hasConcept C2779530757 @default.
- W3089231566 hasConcept C28490314 @default.
- W3089231566 hasConcept C31258907 @default.
- W3089231566 hasConcept C33923547 @default.
- W3089231566 hasConcept C41008148 @default.
- W3089231566 hasConcept C46312422 @default.
- W3089231566 hasConcept C50644808 @default.
- W3089231566 hasConcept C9652623 @default.
- W3089231566 hasConceptScore W3089231566C108583219 @default.
- W3089231566 hasConceptScore W3089231566C111472728 @default.
- W3089231566 hasConceptScore W3089231566C126780896 @default.
- W3089231566 hasConceptScore W3089231566C138885662 @default.
- W3089231566 hasConceptScore W3089231566C144024400 @default.
- W3089231566 hasConceptScore W3089231566C14999030 @default.
- W3089231566 hasConceptScore W3089231566C154945302 @default.
- W3089231566 hasConceptScore W3089231566C177291462 @default.
- W3089231566 hasConceptScore W3089231566C194257627 @default.
- W3089231566 hasConceptScore W3089231566C202444582 @default.
- W3089231566 hasConceptScore W3089231566C2776257435 @default.
- W3089231566 hasConceptScore W3089231566C2779530757 @default.
- W3089231566 hasConceptScore W3089231566C28490314 @default.
- W3089231566 hasConceptScore W3089231566C31258907 @default.
- W3089231566 hasConceptScore W3089231566C33923547 @default.
- W3089231566 hasConceptScore W3089231566C41008148 @default.
- W3089231566 hasConceptScore W3089231566C46312422 @default.
- W3089231566 hasConceptScore W3089231566C50644808 @default.
- W3089231566 hasConceptScore W3089231566C9652623 @default.
- W3089231566 hasLocation W30892315661 @default.
- W3089231566 hasOpenAccess W3089231566 @default.
- W3089231566 hasPrimaryLocation W30892315661 @default.
- W3089231566 hasRelatedWork W2126887587 @default.
- W3089231566 hasRelatedWork W2731899572 @default.
- W3089231566 hasRelatedWork W2794438528 @default.
- W3089231566 hasRelatedWork W2939353110 @default.
- W3089231566 hasRelatedWork W2941846814 @default.
- W3089231566 hasRelatedWork W2948658236 @default.
- W3089231566 hasRelatedWork W2949506716 @default.
- W3089231566 hasRelatedWork W3009238340 @default.
- W3089231566 hasRelatedWork W3215138031 @default.
- W3089231566 hasRelatedWork W4230611425 @default.
- W3089231566 isParatext "false" @default.
- W3089231566 isRetracted "false" @default.
- W3089231566 magId "3089231566" @default.
- W3089231566 workType "article" @default.