8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Kalman-Filter Based Join Cost for Unit-Selection Speech Synthesis

Jithendra Vepa, Simon King

University of Edinburgh, U.K.

We introduce a new method for computing join cost in unit-selection speech synthesis which uses a linear dynamical model (also known as a Kalman filter) to model line spectral frequency trajectories. The model uses an underlying subspace in which it makes smooth, continuous trajectories. This subspace can be seen as an analogy for underlying articulator movement. Once trained, the model can be used to measure how well concatenated speech segments join together. The objective join cost is based on the error between model predictions and actual observations. We report correlations between this measure and mean listener scores obtained from a perceptual listening experiment. Our experiments use a state-of-the art unit-selection text-to-speech system: rVoice from Rhetorical Systems Ltd.

Full Paper

Bibliographic reference.  Vepa, Jithendra / King, Simon (2003): "Kalman-filter based join cost for unit-selection speech synthesis", In EUROSPEECH-2003, 293-296.