FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1980653762> ?p ?o ?g. }

• W1980653762 endingPage "208" @default.
• W1980653762 startingPage "181" @default.
• W1980653762 abstract "Variability has been one of the major challenges for both theoretical understanding and computer synthesis of speech prosody. In this paper we show that economical representation of variability is the key to effective modeling of prosody. Specifically, we report the development of PENTAtrainer—A trainable yet deterministic prosody synthesizer based on an articulatory–functional view of speech. We show with testing results on Thai, Mandarin and English that it is possible to achieve high-accuracy predictive synthesis of fundamental frequency contours with very small sets of parameters obtained through stochastic learning from real speech data. The first key component of this system is syllable-synchronized sequential target approximation—implemented as the qTA model, which is designed to simulate, for each tonal unit, a wide range of contextual variability with a single invariant target. The second key component is the automatic learning of function-specific targets through stochastic global optimization, guided by a layered pseudo-hierarchical functional annotation scheme, which requires the manual labeling of only the temporal domains of the functional units. The results in terms of synthesis accuracy demonstrate that effective modeling of the contextual variability is the key also to effective modeling of function-related variability. Additionally, we show that, being both theory-based and trainable (hence data-driven), computational systems like PENTAtrainer can serve as an effective modeling tool in basic research, with which the level of falsifiability in theory testing can be raised, and also a closer link between basic and applied research in speech science can be developed." @default.
• W1980653762 created "2016-06-24" @default.
• W1980653762 creator A5003455071 @default.
• W1980653762 creator A5049702508 @default.
• W1980653762 date "2014-02-01" @default.
• W1980653762 modified "2023-09-26" @default.
• W1980653762 title "Toward invariant functional representations of variable surface fundamental frequency contours: Synthesizing speech melody via model-based stochastic learning" @default.
• W1980653762 cites W116066295 @default.
• W1980653762 cites W162654330 @default.
• W1980653762 cites W1965426357 @default.
• W1980653762 cites W1966958746 @default.
• W1980653762 cites W1969349521 @default.
• W1980653762 cites W1974537583 @default.
• W1980653762 cites W1978260220 @default.
• W1980653762 cites W1978440078 @default.
• W1980653762 cites W1980605799 @default.
• W1980653762 cites W1986639080 @default.
• W1980653762 cites W1989235927 @default.
• W1980653762 cites W1990448242 @default.
• W1980653762 cites W1995118599 @default.
• W1980653762 cites W1996363348 @default.
• W1980653762 cites W2001540534 @default.
• W1980653762 cites W2003486335 @default.
• W1980653762 cites W2011573972 @default.
• W1980653762 cites W2020738862 @default.
• W1980653762 cites W2023003522 @default.
• W1980653762 cites W2024060531 @default.
• W1980653762 cites W2030438891 @default.
• W1980653762 cites W2034970380 @default.
• W1980653762 cites W2038276123 @default.
• W1980653762 cites W2038784064 @default.
• W1980653762 cites W2042016475 @default.
• W1980653762 cites W2045254591 @default.
• W1980653762 cites W2048449762 @default.
• W1980653762 cites W2052436446 @default.
• W1980653762 cites W2056133372 @default.
• W1980653762 cites W2058211894 @default.
• W1980653762 cites W2059779510 @default.
• W1980653762 cites W2061698901 @default.
• W1980653762 cites W2066452495 @default.
• W1980653762 cites W2069859485 @default.
• W1980653762 cites W2071617451 @default.
• W1980653762 cites W2073477925 @default.
• W1980653762 cites W2076258817 @default.
• W1980653762 cites W2078915496 @default.
• W1980653762 cites W2081724349 @default.
• W1980653762 cites W2086649597 @default.
• W1980653762 cites W2093017178 @default.
• W1980653762 cites W2093414802 @default.
• W1980653762 cites W2093820993 @default.
• W1980653762 cites W2102601039 @default.
• W1980653762 cites W2105036718 @default.
• W1980653762 cites W2112264201 @default.
• W1980653762 cites W2113104907 @default.
• W1980653762 cites W2116043656 @default.
• W1980653762 cites W2117897510 @default.
• W1980653762 cites W2120661116 @default.
• W1980653762 cites W2121399170 @default.
• W1980653762 cites W2126289105 @default.
• W1980653762 cites W2137401844 @default.
• W1980653762 cites W2151929554 @default.
• W1980653762 cites W2162304437 @default.
• W1980653762 cites W2317392553 @default.
• W1980653762 cites W2330979245 @default.
• W1980653762 cites W2809808690 @default.
• W1980653762 cites W2988239832 @default.
• W1980653762 cites W4205359331 @default.
• W1980653762 cites W4245531607 @default.
• W1980653762 cites W4299739251 @default.
• W1980653762 cites W52922326 @default.
• W1980653762 cites W56103664 @default.
• W1980653762 cites W64927310 @default.
• W1980653762 doi "https://doi.org/10.1016/j.specom.2013.09.013" @default.
• W1980653762 hasPublicationYear "2014" @default.
• W1980653762 type Work @default.
• W1980653762 sameAs 1980653762 @default.
• W1980653762 citedByCount "49" @default.
• W1980653762 countsByYear W19806537622014 @default.
• W1980653762 countsByYear W19806537622015 @default.
• W1980653762 countsByYear W19806537622016 @default.
• W1980653762 countsByYear W19806537622017 @default.
• W1980653762 countsByYear W19806537622018 @default.
• W1980653762 countsByYear W19806537622019 @default.
• W1980653762 countsByYear W19806537622020 @default.
• W1980653762 countsByYear W19806537622021 @default.
• W1980653762 countsByYear W19806537622022 @default.
• W1980653762 countsByYear W19806537622023 @default.
• W1980653762 crossrefType "journal-article" @default.
• W1980653762 hasAuthorship W1980653762A5003455071 @default.
• W1980653762 hasAuthorship W1980653762A5049702508 @default.
• W1980653762 hasBestOaLocation W19806537622 @default.
• W1980653762 hasConcept C121332964 @default.
• W1980653762 hasConcept C14999030 @default.
• W1980653762 hasConcept C154945302 @default.
• W1980653762 hasConcept C159985019 @default.
• W1980653762 hasConcept C168167062 @default.
• W1980653762 hasConcept C17744445 @default.
• W1980653762 hasConcept C190470478 @default.

• next