Formant Trajectories for Acoustic-to-Articulatory Inversion
Authors / Editors
Research Areas
No matching items found.
Publication Details
Output type: Other
Author list: Ozbek IY, Hasegawa-Johnson M, Demirekler M
Publication year: 2009
Start page: 2783
End page: 2786
Number of pages: 4
ISBN: 978-1-61567-692-7
Languages: English-Great Britain (EN-GB)
Abstract
This work examines the utility of formant frequencies and their energies in acoustic-to-articulatory inversion. For this purpose, formant frequencies and formant spectral amplitudes are automatically estimated from audio, and are treated as observations for the purpose of estimating electromagnetic articulography (EMA) coil positions. A mixture Gaussian regression model with mel-frequency cepstral (MFCC) observations is modified by using formants and energies to either replace or augment the MFCC observation vector. The augmented observation results in 3.4% lower RMS error, and 2% higher correlation coefficient, than the baseline MFCC observation. Improvement is especially good for stop consonants, possibly because formant tracking provides information about the acoustic resonances that would be otherwise unavailable during stop closure and release.
Keywords
acoustic-to-articulatory inversion, formant tracking, GMM regression
Documents
No matching items found.
