Automatic Labeling of Phrase Accents in German

In this paper a method for the automatic labeling of phrase ac-cents is described, based on a large text corpus that has been generated automatically and read by 100 speakers. Perception experiments on a subset of 500 utterances show a high agreement between the automatically generated accent labels and the judg-ment scores obtained. We computed different prosodic feature vectors from the speech signal for each syllable and trained dif-ferent Gaussian distribution classifiers and artificial neural net-works using the automatically generated accent labels. Recog-nition rates of up to 83 % could be achieved for the distinction of accentuated vs. unaccentuated syllables. Similar results could be obtained for the comparison of the listeners judgments with the automatic classification. I