FSM and k-nearest-neighbor for corpus based video-realistic audio-visual synthesis

Christian Weiss. FSM and k-nearest-neighbor for corpus based video-realistic audio-visual synthesis. In INTERSPEECH 2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005. pages 2537-2540, ISCA, 2005. [doi]

Abstract

Abstract is missing.