Split Time Warping Of Speech For Robust Automatic Dialogue Replacement Host Publication: Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet Authors: P. Soens and W. Verhelst Publication Date: Jun. 2007 Number of Pages: 4
Abstract: In soundtrack production for film and video, new dialogue is often recorded in a studio and used to replace the original dialogue recorded during filming. This 'dialogue replacement' introduces mismatches between the words an audience perceives and the lip movements in the picture. To resolve this problem, synchronization systems have been developed that allow for automatically replacing the original location recordings with re-recorded studio dialogues. However, these systems lack robustness and often deliver time-scaled dialogue that is either insufficiently synchronized with the reference dialogue, of poor quality, or both. In this paper, we propose an improvement to the robustness of automatic time synchronization of speech, which consists of splitting up the procedure in two steps: a first step determines the timing relationship between the recordings and a second step calculates the desired time scaling.
|