FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2561088501> ?p ?o ?g. }

• W2561088501 abstract "Statistical Parametric Speech Synthesis (SPSS) offers flexibility and computational advantage compared to other methods for Text-to-Speech Synthesis. While the speech output is intelligible, statistically trained voices are less natural due to the amount of signal processing and statistical averaging that goes into building the models. Much of the blame for the lack of naturalness falls on the inappropriate and monotonous prosody in synthesized speech. The voice source, which directly effects the prosody, is a complementary source of information than the vocal tract and has its own patterns that need to be dealt with appropriately. Under this hypothesis, this thesis investigates the representations and optimal strategies for prosody modelling within the SPSS paradigm. We propose the Statistical Phrase/Accent Model (SPAM) of intonation as a framework that is both (i) a computational model with associated training and synthesis methods for prosody and (ii) has strong theoretical basis for prosodic description. The SPAM framework combines the strengths of existing complementary views of intonation like Autosegmental Metrical Phonology, Production paradigms like the Fujisaki Model and purely computational approaches like the TILT model. We demonstrate Accent Groups, a new data derived phonological unit, as the optimal representational level to model Pitch accents and integrate it within a multi-tier phonological model to synthesize natural and expressive intonation contours. In addition to improving text-to-speech synthesis, the framework is shown to improve voice conversion, both intra-lingually across speakers, and cross-lingually across languages. We apply the proposed techniques on synthesis of Audiobooks by incorporating richer semantic and contextual features beyond the sentence. We also look at the closely related problem of voice conversion within the SPAM framework to more effectively capture the speaking style of a target speaker. The techniques are also applied for the case of cross-lingual voice conversion, in the context of speech-to-speech machine translation which aims to automatically dub a video into a target language, while preserving the speaker’s intent in the original language after translation. Appropriate objective and subjective evaluations are conducted to show the performance of the proposed techniques." @default.
• W2561088501 created "2017-01-06" @default.
• W2561088501 creator A5068922218 @default.
• W2561088501 date "2013-01-01" @default.
• W2561088501 modified "2023-09-27" @default.
• W2561088501 title "Intra-Lingual and Cross-Lingual Prosody Modelling" @default.
• W2561088501 cites W105761736 @default.
• W2561088501 cites W113498433 @default.
• W2561088501 cites W116754203 @default.
• W2561088501 cites W138654469 @default.
• W2561088501 cites W141349824 @default.
• W2561088501 cites W1500192039 @default.
• W2561088501 cites W1503285781 @default.
• W2561088501 cites W1505264225 @default.
• W2561088501 cites W1508977358 @default.
• W2561088501 cites W1523135049 @default.
• W2561088501 cites W1527151497 @default.
• W2561088501 cites W1543890555 @default.
• W2561088501 cites W1553896573 @default.
• W2561088501 cites W1567156305 @default.
• W2561088501 cites W1567666748 @default.
• W2561088501 cites W1570629387 @default.
• W2561088501 cites W1583314545 @default.
• W2561088501 cites W159170959 @default.
• W2561088501 cites W1598851216 @default.
• W2561088501 cites W1798610767 @default.
• W2561088501 cites W1849169576 @default.
• W2561088501 cites W1935012542 @default.
• W2561088501 cites W1965568387 @default.
• W2561088501 cites W1970346372 @default.
• W2561088501 cites W1973923101 @default.
• W2561088501 cites W1987994475 @default.
• W2561088501 cites W1990332175 @default.
• W2561088501 cites W1990448242 @default.
• W2561088501 cites W1997035035 @default.
• W2561088501 cites W1999885698 @default.
• W2561088501 cites W2000513720 @default.
• W2561088501 cites W2005465272 @default.
• W2561088501 cites W2010795687 @default.
• W2561088501 cites W2010800472 @default.
• W2561088501 cites W2013996527 @default.
• W2561088501 cites W202879582 @default.
• W2561088501 cites W2034724441 @default.
• W2561088501 cites W2048389584 @default.
• W2561088501 cites W2063292270 @default.
• W2561088501 cites W2093414802 @default.
• W2561088501 cites W2099352211 @default.
• W2561088501 cites W2100649345 @default.
• W2561088501 cites W2102267302 @default.
• W2561088501 cites W2104779640 @default.
• W2561088501 cites W2105927960 @default.
• W2561088501 cites W2112390707 @default.
• W2561088501 cites W2116043656 @default.
• W2561088501 cites W2119138452 @default.
• W2561088501 cites W2120605154 @default.
• W2561088501 cites W2123003832 @default.
• W2561088501 cites W2124807415 @default.
• W2561088501 cites W2129142580 @default.
• W2561088501 cites W2130416582 @default.
• W2561088501 cites W2131864930 @default.
• W2561088501 cites W2133300417 @default.
• W2561088501 cites W2138672527 @default.
• W2561088501 cites W2143777890 @default.
• W2561088501 cites W2145880678 @default.
• W2561088501 cites W2148846882 @default.
• W2561088501 cites W2149017325 @default.
• W2561088501 cites W2150612204 @default.
• W2561088501 cites W2150658333 @default.
• W2561088501 cites W2150791533 @default.
• W2561088501 cites W2151144629 @default.
• W2561088501 cites W2152834109 @default.
• W2561088501 cites W2154280657 @default.
• W2561088501 cites W2154765984 @default.
• W2561088501 cites W2154920538 @default.
• W2561088501 cites W2164107060 @default.
• W2561088501 cites W2166947141 @default.
• W2561088501 cites W2186079634 @default.
• W2561088501 cites W22168010 @default.
• W2561088501 cites W2232237094 @default.
• W2561088501 cites W2244925781 @default.
• W2561088501 cites W2295027170 @default.
• W2561088501 cites W23142961 @default.
• W2561088501 cites W2330979245 @default.
• W2561088501 cites W2395672826 @default.
• W2561088501 cites W2397670763 @default.
• W2561088501 cites W2399732622 @default.
• W2561088501 cites W2400063444 @default.
• W2561088501 cites W2402765441 @default.
• W2561088501 cites W2402998908 @default.
• W2561088501 cites W242082043 @default.
• W2561088501 cites W2551677481 @default.
• W2561088501 cites W28194048 @default.
• W2561088501 cites W2917438849 @default.
• W2561088501 cites W4927070 @default.
• W2561088501 cites W583042331 @default.
• W2561088501 cites W70888257 @default.
• W2561088501 cites W1607586541 @default.
• W2561088501 hasPublicationYear "2013" @default.
• W2561088501 type Work @default.
• W2561088501 sameAs 2561088501 @default.

• next