Compression enhancement of video motion of mouth region using joint audio and video coding

We propose an application that utilises audio and video data dependencies to achieve additional video compression in low-bit rate encoding systems such as: H.263+ video coding and G.723.1 audio coding standards. The joint correlation of synchronized audio and motion parameters has been proved to exist. A joint performance of principal component analysis (PCA) by Karhunen-Loeve expansions (KL) and tree-structured vector quantization algorithms (TSVQ) based on Linde-Buzo-Gray (LBG) and competitive learning (CL) techniques achieve as much as 60% bit reduction for the motion in the mouth region (1% of the overall output bit rate of a P frame) and provide the same motion-compensated image quality in high picture formats. We show performance evaluations that determine the optimal audio parameters, such as linear predictive coefficients (LPC) or line spectrum pairs (LSP), and determine the nature of the motion parameter in each macroblock of the mouth region when using advanced prediction mode (APM) video coding