de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Can unquantised articulatory feature continuums be modelled?

MPS-Authors
There are no MPG-Authors available
Locator
There are no locators available
Fulltext (public)

DA9A17B2d01.pdf
(Publisher version), 580KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Scharenborg, O., & Wan, V. (2007). Can unquantised articulatory feature continuums be modelled? In INTERSPEECH 2007 - 8th Annual Conference of the International Speech Communication Association (pp. 2473-2476). ISCA Archive.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0012-D219-F
Abstract
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.