Matched filter design for diphone subspace models
Klaus Reinhard, Mahesan Niranjan · 2002
Considering the perceptual importance of phonetic transitions as minimal contextual variant units, this paper addresses the problem by modelling explicitly interphone dynamics covered in diphones. Subspace projections based on a time-constrained PCA (TC-PCA) are developed which focus on the temporal evolution. They reveal characteristic trajectories present in a low-dimensional spectral representation facilitating robust parameter estimation and simultaneously optimise the discriminant information. A matched filter design is applied to a multiple hypotheses rescoring scheme which enables operating in very low-dimensional parameter space. Using such multiple hypotheses paradigm the complementary information effectiveness of modelling explicitly inter-phone dynamics covered in diphones can be shown using the TIMIT database, resulting in improved phone error rates.