ing visual prosody across speakers and face areas Erin Cvejic, Jeesun Kim, Chris Davis MARCS Auditory Laboratories, University of Western Sydney, Milperra, Australia [email protected], [email protected], [email protected]

Studies of the relationship between prosody and the topic structure of longer discourses have tended to focus on intonational cues, most specifically fundamental frequency (F0). However, this may limit the kinds of topic structure it is possible to identify. A case study of two speakers shows that including speech rate along with F0 factors in an analysis of the prosody of topic structure can b...

In these days, there are many e-learning system for studying by yourself. In these systems, learner can make their own pacing in for each learning section. But many learner needs more shorter term pacing adjusted to individual motivation and feeling in one session. Many video learning system has lack of interaction. On the other hand, novel game type e-learning system can interact to learner. B...

Speech is the most direct and intuitive form of human communication. Speaker uses to emphasize his utterance a set of non-verbal features. It is called prosody. The prosody serves a critical information for the recognition and understanding system. This paper describes an idea to use data warehouse properties for storage of prosody features. The work presented in this paper was supported by the...

This paper concerns the evaluation of prosody prediction at the symbolic level, in particular the locations of pitch accents and intonational boundaries. One evaluation method is to ask an expert to annotate text prosodically, and to compare the system’s predictions with this reference. However, this ignores the issue of optionality: there is usually more than one acceptable way to place accent...

The paper presents some of the problems of classification and annotation of speech sounds that have their own phonetic content, phonological function, and prosody, but they do not have an adequate linguistic (or text) representation. One of the most important facts about these "nonverbal vocal gestures" is that they often have a rich semantic content and they play an important role in expressiv...

.............................................................................................................................. ii Acknowledgements ............................................................................................................ iii Table of

We examine the dynamics of VOT in Polish stops under lexical stress and focus. We elicit real Polish words containing voiced and voiceless stop+/a/ syllables in primary, secondary and unstressed, as well as focus positions. We also correlate VOT with speech rate estimated on the basis of equisyllabic word length. Our results show that the relationships between prosody and VOT are consistent wit...

To use impersonation in order to entertain it is necessary to be aware of the target speaker’s speech behaviour and characteristic features. Does a professional impersonator really change his own voice quality and speech behaviour substantially in his impersonation, or does he only exaggerate some features of the target speaker to cheat and entertain the audience? The results of this analysis p...