In this paper, we present a greedy graph search algorithm that yields vastly superior performance and allows real-time motion synthesis from a large database of motions.
Data-driven approaches have been successfully used for realistic visual speech synthesis. However, little effort has been devoted to real-time lip-synching for interactive applications. In particular, algorithms that are based on a graph of motions are notorious for their exponential complexity. In this paper, we present a greedy graph search algorithm that yields vastly superior performance and allows real-time motion synthesis from a large database of motions. The time complexity of the algorithm is linear with respect to the size of an input utterance. In our experiments, the synthesis time for an input sentence of average length is under a second.
NOT SPECIFICALLY THE VINYL ARTIFACT WRAPPEDIN CARDBOARD.It is our proposal to take advantage of the positive aspects of a negative trend afflictingthe record industry today: home taping of material released on vinyl.First of all, we must realize that the taping of albums is not necessarily motivated by consumer'stinginess.' If a consumer makes a home tape from a disc, that copy will probably sound better than a commerciallymanufactured high-speed duplication cassette legitimately released by the company. We propose to acquire the rights to digitally duplicate THE BEST of every record company'sdifficult-to-move Quality Catalog Items [Q.C.I.], store them in a central processing location, and have themaccessible by phone or cable TV, directly patchable into the user's home taping appliances, with the option of directdigital-to-digital transfer to the F-l (SONY consumer-level digital tape encoder), Beta Hi-Fi, or ordinary analogcassette (requiring the installation of a rentable D-A converter in the phone itself.
For, if Science sometimes succeeds with its great ingenuity in explaining some of such stoppages, retrograde motions, angles outside the orbits, &c., &c., by appearances resulting from the inequality of their progress and ours in the course of our mutual and respective orbits, we still know that there are others, and "very real and considerable deviations," according to Herschell, "which cannot be explained except by the mutual and irregular action of those planets and by the perturbing influence of the Sun."