5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Modeling Segmental Duration with Multivariate Adaptive Regression Splines

Marcel Riedi

Institut TIK, ETH Zürich, Zürich, Switzerland

The application of "Multivariate Adaptive Regression Splines" (MARS) to the problem of modeling duration of a set of segments used in a text-to-speech system for German is presented. MARS is a technique to estimate general functions of high-dimensional arguments given sparse data. It automatically selects the parameters and the structure of the model based on data available. The result is a model with a correlation coefficient between observed and predicted durations of a test set of . Besides highly accurate predicting durations, a MARS model also allows interpretation of its structure, demonstrated in this study by analyses of factor importance and interactions of the MARS model.

Full Paper

Bibliographic reference.  Riedi, Marcel (1997): "Modeling segmental duration with multivariate adaptive regression splines", In EUROSPEECH-1997, 2627-2630.