Interspeech'2005 - Eurospeech
Vocal tract data from 3D cine-MRI are used together with synchronised acoustics to evaluate a linear regression model for inversion. The first two principal components of vocalic area functions are predicted with correlations 0.99 and 0.97 respectively, from 24 FFT-cepstra measured in the frequency band 0-4 kHz. This best regression model together with the two component representation yields mean absolute errors of 0.37 cm2 in section area and 0.15 cm in vocal tract length.
Bibliographic reference. Mokhtari, Parham / Kitamura, Tatsuya / Takemoto, Hironori / Honda, Kiyoshi (2005): "Vocal tract area function inversion by linear regression of cepstrum", In INTERSPEECH-2005, 3201-3204.