Bayesian networks for phone duration prediction

O. Goubanova, S. King

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

In a text-to-speech system, the duration of each phone may be predicted by a duration model. This model is usually trained using a database of phones with known durations; each phone (and the context it appears in) is characterised by a feature vector that is composed of a set of linguistic factor values. We describe the use of a graphical model -- a Bayesian network -- for predicting the duration of a phone, given the values for these factors. The network has one discrete variable for each of the linguistic factors and a single continuous variable for the phone's duration. Dependencies between variables (or the lack of them) are represented in the BN structure by arcs (or missing arcs) between pairs of nodes. During training, both the topology of the network and its parameters are learned from labelled data. We compare the results of the BN model with results for sums of products and CART models on the same data. In terms of the root mean square error, the BN model performs much better than both CART and SoP models. In terms of correlation coefficient, the BN model performs better than the SoP model, and as well as the CART model. A BN model has certain advantages over CART and SoP models. Training SoP models requires a high degree of expertise. CART models do not deal with interactions between factors in any explicit way. As we demonstrate, a BN model can also make accurate predictions of a phone's duration, even when the values for some of the linguistic factors are unknown.
Original languageEnglish
Pages (from-to)301-311
Number of pages11
JournalSpeech Communication
Issue number4
Publication statusPublished - Apr 2008

Keywords / Materials (for Non-textual outputs)

  • Text-to-speech
  • Bayesian networks
  • Duration modelling
  • Sums of products
  • Classification and regression trees


Dive into the research topics of 'Bayesian networks for phone duration prediction'. Together they form a unique fingerprint.

Cite this