8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Can Unquantised Articulatory Feature Continuums be Modelled?

Odette Scharenborg (1), Vincent Wan (2)

(1) Radboud University Nijmegen, The Netherlands
(2) University of Sheffield, UK

Articulatory feature (AF) modelling of speech has received a considerable amount of attention in automatic speech recognition research. Although termed ‘articulatory’, previous definitions make certain assumptions that are invalid, for instance, that articulators ‘hop’ from one fixed position to the next. In this paper, we studied two methods, based on support vector classification (SVC) and regression (SVR), in which the articulation continuum is modelled without being restricted to using discrete AF value classes. A comparison with a baseline system trained on quantised values of the articulation continuum showed that both SVC and SVR outperform the baseline for two of the three investigated AFs, with improvements up to 5.6% absolute.

Full Paper

Bibliographic reference.  Scharenborg, Odette / Wan, Vincent (2007): "Can unquantised articulatory feature continuums be modelled?", In INTERSPEECH-2007, 2473-2476.