In this contribution an algorithm for the automatic assignment of sentence accents in written Dutch, developed by Kager and Quené, is evaluated experimentally. Results show that the output of the algorithm is judged significantly more adequate than accents randomly distributed over content words but significantly less adequate than the accents produced by a trained news broadcaster and those realized by the majority of the subjects themselves. Insight was sought into the basis of the adequacy judgments and suggestions are made for the improvement of the algorithm.
Bibliographic reference. Bezooijen, Renée van / Pols, Louis C. W. (1989): "Evaluation of a sentence accentuation algorithm for a dutch text-to-speech system", In EUROSPEECH-1989, 1218-1221.