Articulatory feature recognition using dynamic Bayesian networks

J. Frankel, M. Wester, S. King

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended to be a component of a speech recognizer that avoids the problems of conventional ``beads-on-a-string'' phoneme-based models. We demonstrate that the model gives superior recognition of articulatory features from the speech signal compared with a stateof- the art neural network system. We also introduce a training algorithm that offers two major advances: it does not require time-aligned feature labels and it allows the model to learn a set of asynchronous feature changes in a data-driven manner.
Original languageEnglish
Pages (from-to)620-640
Number of pages21
JournalComputer Speech and Language
Issue number4
Publication statusPublished - 1 Oct 2007


Dive into the research topics of 'Articulatory feature recognition using dynamic Bayesian networks'. Together they form a unique fingerprint.

Cite this