Automatic detection of prominence in speech is an important task for many spoken language applications. However, most previous approaches rely on the availability of a corpus that is annotated with prosodic labels in order to train classifiers, therefore lacking generality beyond high-resourced languages. In this paper, we propose an algorithm for the automatic detection of sentence prominence ...

The present study investigates the acoustic manifestation and phonological nature of prominences induced by dual and multiple focuses in Standard Chinese (hereinafter SC). Results show that double focus exerted two prominences in the target sentence and these two prominences performed similar acoustic manifestations. However, under a multiple focus condition, only the rightmost focused constitu...

The legal principle of accession suggests that people sometimes extend ownership a prominent item to related objects, resources, and benefits. For example, might assume whoever owns large land mass is also likely possess surrounding islands. In three experiments on 4–7-year-olds (N = 526) adults 498), we find prominence affects inductive inferences about both liking. Experiment 1, children were...

In this letter, we present useful features accounting for pronunciation prominence and propose a classification technique for prominence detection. A set of phone-specific features are extracted based on a forced alignment of the test pronunciation provided by a speech recognition system. These features are then applied to the traditional classifiers such as the support vector machine (SVM), ar...

0. Combinations of Sonority and Stress In their analysis of Imdlawn Tashlhiyt Berber syllabification, Prince and Smolensky (1993) postulate that different types of prominence, such as sonority and syllabicity, should align—a phenomenon they term prominence alignment. This concept is implemented by Prince and Smolensky using families of inherently-ranked constraints that are derived from combini...