Time-frequency relevant features for critical articulators movement inference

This paper presents a method to study the distribution of the articulatory information on time-frequency representation calculated from the acoustic speech signal, whose parametrization is achieved using the wavelet packet transform. The main focus is on measuring the relevant acoustic information, in terms of statistical association, for the inference of critical articulator positions. The rank correlation Kendall coefficient is used as the relevance measure. The maps of relevant time-frequency features are calculated for the MOCHA-TIMIT database, where the articulatory information is represented by trajectories of specific positions in the vocal tract. Relevant maps are estimated on specific phones, for which a given articulator is known to be critical. The usefulness of the relevant maps is tested in an acoustic-to-articulatory mapping system based on gaussian mixture models.