Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025800766> ?p ?o ?g. }
- W3025800766 abstract "This thesis investigates the problem of producing perceptually realistic facial animation of expressions and speech. It spans several different areas of work, from capture and representation of facial dynamics through to analysis and synthesis of expressive 3D animation sequences. For this purpose, a database of 3D facial scans was collected from 16 subjects each performing 7 expressions. Ekman’s set of 6 cross-culturally recognised emotions and a neutral emotion were used. Several representations of facial expressions are compared: morphable model, its extension to tensor space and so on. A multilinear tensor-based morphable model is a powerful tool as it permits to independently control identity and expression. However, its high computational cost and non-intuitive set of parameters have motivated us to opt for a standard 3D morphable modelling approach. We propose a novel algorithm for mapping between motion capture data, projected to spatially low resolution (19 markers) 3D model space, and spatially high resolution (3300 vertices and colour texture) 3D morphable model space. This radial basis function based mapping preserves the temporal characteristics of motion capture data and the level of detail of high resolution 3D scans. The single-subject model is extended to animate other subjects based on a single 3D scan or a photograph. An additional model is needed to represent the variation between individual expression styles. The relation between audio and visual features is analysed based on a 4D dataset of expressive speech. The dataset consists of 3D scans of a single subject, recorded at 60 Hz, and a synchronised audio at 44.1 kHz. The speech corpus contains 235 phonetically balanced expressive English sentences, recorded in 6 emotions and neutral. Audio features consist of fundamental frequency F0, duration, energy and Mel-frequency cepstral coefficients. Face was separated into overlapping facial regions. Visual signal was then used to compute temporal visual features for each facial region. We concentrate on the upper face region due to its high expressive content and lesser contamination by articulation. Phoneme, word and sentence level audio-visual analysis is performed within each emotional category and among all emotional categories. Although, initial results show a promising connection between dynamics of audio and visual features for some emotions, significant intra-class variation exists for the others. Results demonstrate that dynamics and intensity of expressive content within and across sentences are highly influenced by their linguistic content. This work shows that the effect of temporal variation of expressive content is statistically significant and should be taken into account in visual speech synthesis. Further investigation is necessary with a more controlled setup. This thesis provides the foundation for further research towards the understanding of the connection between expressive content and visual dynamics during speech and achieving perceptually realistic animation of a talking head." @default.
- W3025800766 created "2020-05-21" @default.
- W3025800766 creator A5027632423 @default.
- W3025800766 date "2011-01-01" @default.
- W3025800766 modified "2023-09-22" @default.
- W3025800766 title "Analysis, Modelling and Animation of Emotional Speech in 3D." @default.
- W3025800766 cites W1261896931 @default.
- W3025800766 cites W143827410 @default.
- W3025800766 cites W1496403746 @default.
- W3025800766 cites W1521793179 @default.
- W3025800766 cites W1525214210 @default.
- W3025800766 cites W1534304300 @default.
- W3025800766 cites W1544596136 @default.
- W3025800766 cites W1554803342 @default.
- W3025800766 cites W1564870812 @default.
- W3025800766 cites W1571461735 @default.
- W3025800766 cites W1603817919 @default.
- W3025800766 cites W1604919928 @default.
- W3025800766 cites W1940107713 @default.
- W3025800766 cites W1963826206 @default.
- W3025800766 cites W1968811590 @default.
- W3025800766 cites W1970233340 @default.
- W3025800766 cites W1975089519 @default.
- W3025800766 cites W1987839992 @default.
- W3025800766 cites W1990717412 @default.
- W3025800766 cites W1991042426 @default.
- W3025800766 cites W1994757710 @default.
- W3025800766 cites W1995875735 @default.
- W3025800766 cites W2000366549 @default.
- W3025800766 cites W2004195401 @default.
- W3025800766 cites W2004312117 @default.
- W3025800766 cites W2009375902 @default.
- W3025800766 cites W2013912476 @default.
- W3025800766 cites W2014555571 @default.
- W3025800766 cites W2014621385 @default.
- W3025800766 cites W2015394094 @default.
- W3025800766 cites W2022012885 @default.
- W3025800766 cites W2022890264 @default.
- W3025800766 cites W2026871208 @default.
- W3025800766 cites W2026926678 @default.
- W3025800766 cites W2036345186 @default.
- W3025800766 cites W2038952578 @default.
- W3025800766 cites W2041596166 @default.
- W3025800766 cites W2045863238 @default.
- W3025800766 cites W2046002001 @default.
- W3025800766 cites W2046677541 @default.
- W3025800766 cites W2046911213 @default.
- W3025800766 cites W2050744010 @default.
- W3025800766 cites W2059294779 @default.
- W3025800766 cites W2064400654 @default.
- W3025800766 cites W2072578292 @default.
- W3025800766 cites W2074146319 @default.
- W3025800766 cites W2082229127 @default.
- W3025800766 cites W2084288097 @default.
- W3025800766 cites W2086185113 @default.
- W3025800766 cites W2095156353 @default.
- W3025800766 cites W2096183091 @default.
- W3025800766 cites W2096619076 @default.
- W3025800766 cites W2096741982 @default.
- W3025800766 cites W2097108975 @default.
- W3025800766 cites W2098449997 @default.
- W3025800766 cites W2099634219 @default.
- W3025800766 cites W2102416463 @default.
- W3025800766 cites W2102998034 @default.
- W3025800766 cites W2103772357 @default.
- W3025800766 cites W2105934661 @default.
- W3025800766 cites W2110121428 @default.
- W3025800766 cites W2112890390 @default.
- W3025800766 cites W2113055885 @default.
- W3025800766 cites W2117752179 @default.
- W3025800766 cites W2118789253 @default.
- W3025800766 cites W2120420721 @default.
- W3025800766 cites W2120654454 @default.
- W3025800766 cites W2121647436 @default.
- W3025800766 cites W2122251926 @default.
- W3025800766 cites W2127704440 @default.
- W3025800766 cites W2128070398 @default.
- W3025800766 cites W2131529090 @default.
- W3025800766 cites W2132172443 @default.
- W3025800766 cites W2134571991 @default.
- W3025800766 cites W2135666716 @default.
- W3025800766 cites W2136660755 @default.
- W3025800766 cites W2137293535 @default.
- W3025800766 cites W2141570123 @default.
- W3025800766 cites W2143640516 @default.
- W3025800766 cites W2144481990 @default.
- W3025800766 cites W2146932984 @default.
- W3025800766 cites W2147737730 @default.
- W3025800766 cites W2147885303 @default.
- W3025800766 cites W2148952796 @default.
- W3025800766 cites W2148985157 @default.
- W3025800766 cites W2152826865 @default.
- W3025800766 cites W2153763188 @default.
- W3025800766 cites W2154611638 @default.
- W3025800766 cites W2156671261 @default.
- W3025800766 cites W2158054470 @default.
- W3025800766 cites W2160126058 @default.
- W3025800766 cites W2162598851 @default.
- W3025800766 cites W2162975013 @default.
- W3025800766 cites W2177205626 @default.