12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Optimal Models of Prosodic Prominence Using the Bayesian Information Criterion

Tim Mahrt, Jui-Ting Huang, Yoonsook Mo, Margaret Fleck, Mark Hasegawa-Johnson, Jennifer Cole

University of Illinois at Urbana-Champaign, USA

This study investigated the relation between various acoustic features and prominence. Past research has suggested that duration, pitch, and intensity all play a role in the perception of prominence. In our past work, we found a correlation between these acoustic features and speaker agreement over the placement of prominence. The current study was motivated by a need to enrich our understanding of this correlation. Using the Bayesian information criterion, we show that the best model for a feature that cues prosody is not necessarily a single Gaussian. Rather, the best model depends on the feature. This finding has consequences for our understanding of the role of these features in the perception of prosody and for prosody recognition systems.

Full Paper

Bibliographic reference.  Mahrt, Tim / Huang, Jui-Ting / Mo, Yoonsook / Fleck, Margaret / Hasegawa-Johnson, Mark / Cole, Jennifer (2011): "Optimal models of prosodic prominence using the Bayesian information criterion", In INTERSPEECH-2011, 2037-2040.