A Surficial Pronunciation Model

Abstract: We argue for a surficial pronunciation model: a model without underlying forms. The surficial model outperforms a traditional generative model by a significant margin on conversation speech (Switchboard) as well as on read speech (TIMIT). Our results suggest that the true mapping from underlying forms to surface forms is too complex to be accurately modeled using current techniques, and that we would be best server to model the surface forms directly.

• The complete paper (PDF)

• The complete paper (PostScript)

• BibTex entry

• My homepage ( Peter N. Yianilos )

• See also:
  • A General Decomposition Theorem that Extends Baum-Welch and the Expectation-Maximization Paradigm to Rational Forms
  • Learning String Edit Distance
  • On the Strange a Posteriori degeneracy of Normal Mixtures and Related Reparameterization Theorems (or) Towards EM-style Algorithms for a posteriori Optimization of Normal Mixtures
  • Topics in Computational Hidden State Modeling
  • Finite Growth Models

• Coauthors:
  • Eric Sven Ristad