Detecting Pitch Accents at the Word, Syllable and Vowel Level

The automatic identification of prosodic events such as pitch accent in English has long been a topic of interest to speech researchers, with applications to a variety of spoken language processing tasks. However, much remains to be understood about the best methods for obtaining high accuracy detection. We describe experiments examining the optimal domain for accent analysis. Specifically, we compare pitch accent identification at the syllable, vowel or word level as domains for analysis of acoustic indicators of accent. Our results indicate that a word-based approach is superior to syllableor vowel-based detection, achieving an accuracy of 84.2%.