FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W168087145> ?p ?o ?g. }

• W168087145 abstract "Abstract A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here confronted to German intonation. Training material is the publicly available Siemens Synthesis Corpus that provides spoken utterances for high-quality speech synthesis. We describe the labeling framework and first evaluation results that compares the original prosody of test sentences of this corpus with their prosodic rendering by the proposed model and state-of-the-art systems available on-line on the web. Index Terms : speech synthesis, prosody, evaluation Introduction The trainable prosodic model SFC (Superposition of Functional Contours) has been developed by Holm and Bailly [1-3]. It implements a theoretical model of intonation initially sketched by Auberge [4, 5] that promotes an intimate link between phonetic forms and linguistic functions: metalinguistic functions acting on different discourse units (thus at different scopes) are directly implemented as global multiparametric contours. These metalinguistic functions refer to the general ability of intonation to demarcate phonological units and convey information about the propositional and interactional func tions of these units within the discourse. This trainable prosodic model has been confronted to speech styles (from read speech to spoken maths) and different languages including French, Galician or more recently Chinese [6]. German is of most interest because of its rich morphology and its potentially deep recursive syntactic embedding. Analysis of German prosody notably induces Schreuder and Gilbers [7] to question the Strict Layer Hypothesis [8] and claim for the existence of recursive prosodic phrases. While most quantitative models of German intonation that have been so far applied to speech synthesis use a phonological representation with few levels when not limited to prosodic phrases [9, 10]. We describe here our first efforts in confronting the SFC - that may potentially capture rich embedded performance structures [11] – to German intonation. Our first parameterization of the SFC usi ng limited training material is evaluated against state-of-the-art text-to-speech systems available on the web." @default.
• W168087145 created "2016-06-24" @default.
• W168087145 creator A5056558389 @default.
• W168087145 creator A5071432574 @default.
• W168087145 date "2006-09-17" @default.
• W168087145 modified "2023-09-25" @default.
• W168087145 title "Generating German intonation with a trainable prosodic model" @default.
• W168087145 cites W107046217 @default.
• W168087145 cites W1504955803 @default.
• W168087145 cites W1865834476 @default.
• W168087145 cites W191101173 @default.
• W168087145 cites W1942270970 @default.
• W168087145 cites W1990448242 @default.
• W168087145 cites W2095172853 @default.
• W168087145 cites W2096195361 @default.
• W168087145 cites W2104674061 @default.
• W168087145 cites W2107807958 @default.
• W168087145 cites W2118197641 @default.
• W168087145 cites W2142337420 @default.
• W168087145 cites W2247776648 @default.
• W168087145 cites W2401533136 @default.
• W168087145 cites W2407028210 @default.
• W168087145 cites W2588340457 @default.
• W168087145 cites W281711673 @default.
• W168087145 cites W36044367 @default.
• W168087145 cites W38355094 @default.
• W168087145 cites W39887858 @default.
• W168087145 cites W141443464 @default.
• W168087145 doi "https://doi.org/10.21437/interspeech.2006-593" @default.
• W168087145 hasPublicationYear "2006" @default.
• W168087145 type Work @default.
• W168087145 sameAs 168087145 @default.
• W168087145 citedByCount "3" @default.
• W168087145 countsByYear W1680871452015 @default.
• W168087145 crossrefType "proceedings-article" @default.
• W168087145 hasAuthorship W168087145A5056558389 @default.
• W168087145 hasAuthorship W168087145A5071432574 @default.
• W168087145 hasBestOaLocation W1680871452 @default.
• W168087145 hasConcept C138885662 @default.
• W168087145 hasConcept C154775046 @default.
• W168087145 hasConcept C154945302 @default.
• W168087145 hasConcept C204321447 @default.
• W168087145 hasConcept C2781045179 @default.
• W168087145 hasConcept C28490314 @default.
• W168087145 hasConcept C41008148 @default.
• W168087145 hasConcept C41895202 @default.
• W168087145 hasConceptScore W168087145C138885662 @default.
• W168087145 hasConceptScore W168087145C154775046 @default.
• W168087145 hasConceptScore W168087145C154945302 @default.
• W168087145 hasConceptScore W168087145C204321447 @default.
• W168087145 hasConceptScore W168087145C2781045179 @default.
• W168087145 hasConceptScore W168087145C28490314 @default.
• W168087145 hasConceptScore W168087145C41008148 @default.
• W168087145 hasConceptScore W168087145C41895202 @default.
• W168087145 hasLocation W1680871451 @default.
• W168087145 hasLocation W1680871452 @default.
• W168087145 hasLocation W1680871453 @default.
• W168087145 hasLocation W1680871454 @default.
• W168087145 hasLocation W1680871455 @default.
• W168087145 hasLocation W1680871456 @default.
• W168087145 hasOpenAccess W168087145 @default.
• W168087145 hasPrimaryLocation W1680871451 @default.
• W168087145 hasRelatedWork W1999535306 @default.
• W168087145 hasRelatedWork W2009487810 @default.
• W168087145 hasRelatedWork W2048342080 @default.
• W168087145 hasRelatedWork W2050646096 @default.
• W168087145 hasRelatedWork W2485285282 @default.
• W168087145 hasRelatedWork W2899266101 @default.
• W168087145 hasRelatedWork W2973189658 @default.
• W168087145 hasRelatedWork W4210920262 @default.
• W168087145 hasRelatedWork W577749800 @default.
• W168087145 hasRelatedWork W2289534346 @default.
• W168087145 isParatext "false" @default.
• W168087145 isRetracted "false" @default.
• W168087145 magId "168087145" @default.
• W168087145 workType "article" @default.