From Sound Synthesis to Sound Retrieval and Back Tube. Duration : 55.42 Mins.
Google Tech Talks July 10, 2007 ABSTRACT In this talk I will go over the technological and conceptual ties that exist between some of the current trends in sound generation for music and multimedia applications and the techniques for content based sound retrieval. This is because quite a number of the techniques being worked on for sound retrieval come from the field of sound synthesis and at the same time the new developments in retrieval are being applied and are inspiring new directions in the development of sound generation systems. To explain all this I will use examples from the research carried out in the Music Technology Group at the Pompeu Fabra University of Barcelona, Spain. In...
Keywords: google, howto, sound, synthesis, retrieval, back
Motion Synthesis from Annotations Tube. Duration : 4.45 Mins.
Okan Arikan, David A. Forsyth, James O'Brien This paper describes a framework that allows a user to synthesize human motion while retaining control of its qualitative properties. The user paints a timeline with annotations --- like walk, run or jump --- from a vocabulary which is freely chosen by the user. The system then assembles frames from a motion database so that the final motion performs the specified actions at specified times. The motion can also be forced to pass through particular configurations at particular times, and to go to a particular position and orientation. Annotations can be painted positively (for example, must run), negatively (for example, may not run backwards) or as a don't-care. The system uses a novel search method, based around dynamic programming at several scales, to obtain a solution efficiently so that authoring is interactive. Our results demonstrate that the method can generate smooth, natural-looking motion. The annotation vocabulary can be chosen to fit the application, and allows specification of composite motions (run and jump} simultaneously, for example). The process requires a collection of motion data that has been annotated with the chosen vocabulary. This paper also describes an effective tool, based around repeated use of support vector machines, that allows a user to annotate a large collection of motions quickly and easily so that they may be used with the synthesis algorithm.
Keywords: character, animation, motion, capture, game, development
