We present a new phone-dependent feature weighting scheme that can be used to map articulatory configurations (e.g. EMA) onto vocal tract spectra (e.g. MFCC) through table lookup. The approach consists of assigning feature weights according to a featureís ability to predict the acoustic distance between frames. Since an articulatorís predictive accuracy is phone-dependent (e.g., lip location is a better predictor for bilabial sounds than for palatal sounds), a unique weight vector is found for each phone. Inspection of the weights reveals a correspondence with the expected critical articulators for many phones. The proposed method reduces overall cepstral error by 6% when compared to a uniform weighting scheme. Vowels show the greatest benefit, though improvements occur for 80% of the tested phones.
Bibliographic reference. Felps, Daniel / Geng, Christian / Berger, Michael / Richmond, Korin / Gutierrez-Osuna, Ricardo (2010): "Relying on critical articulators to estimate vocal tract spectra in an articulatory-acoustic database", In INTERSPEECH-2010, 1990-1993.