Adaptive kernel canonical correlation analysis for estimation of task dynamics from acoustics
Frank Rudzicz · 2010
We present a method for acoustic-articulatory inversion whose targets are the abstract tract variables from task dynamic theory. Towards this end we construct a non-linear Hammerstein system whose parameters are updated with adaptive kernel canonical correlation analysis. This approach is notably semi-analytical and applicable to large sets of data. Training behaviour is compared across four kernel functions and prediction of tract variables is shown to be significantly more accurate than state-of-the-art mixture density networks. Index terms: acoustic-articulatory inversion, kernel canonical correlation analysis, task dynamics. 1.