ISCA Archive Interspeech 2007
ISCA Archive Interspeech 2007

A multitask learning perspective on acoustic-articulatory inversion

Korin Richmond

This paper proposes the idea that by viewing an inversion mapping MLP from a Multitask Learning perspective, we may be able to relax two constraints which are inherent in using electromagnetic articulography as a source of articulatory information for speech technology purposes. As a first step to evaluating this idea, we perform an inversion mapping experiment in an attempt to ascertain whether the hidden layer of a "multitask" MLP can act beneficially as a hidden representation that is shared between inversion mapping subtasks for multiple articulatory targets. Our results in the case of the tongue dorsum x-coordinate indicate this is indeed the case and show good promise. Results for the tongue dorsum y-coordinate however are not so clear-cut, and will require further investigation.

doi: 10.21437/Interspeech.2007-656

Cite as: Richmond, K. (2007) A multitask learning perspective on acoustic-articulatory inversion. Proc. Interspeech 2007, 2465-2468, doi: 10.21437/Interspeech.2007-656

  author={Korin Richmond},
  title={{A multitask learning perspective on acoustic-articulatory inversion}},
  booktitle={Proc. Interspeech 2007},