Segmentation research asks how listeners locate word boundaries in the ongoing speech stream. Previous work has identified multiple cues (lexical, segmental, prosodic) which affect perception of boundary placement, but such studies have almost exclusively used careful read speech, rather than speech elicited in a natural communicative context. We report development of a segmentation-oriented corpus of spontaneous speech and assess, by comparison with a parallel read speech corpus, how cues such as lexical stress and word-initial lengthening are modulated by the nature of the communicative context, finding evidence in spontaneous speech of contextually-conditioned hypoarticulation that may impact on boundary perception.
Index Terms: speech segmentation, spontaneous speech, rhythm, word-initial lengthening
Cite as: White, L., Wiget, L., Rauch, O., Mattys, S.L. (2010) Segmentation cues in spontaneous and read speech. Proc. Speech Prosody 2010, paper 218
@inproceedings{white10_speechprosody,
author={Laurence White and Lukas Wiget and Olesya Rauch and Sven L. Mattys},
title={{Segmentation cues in spontaneous and read speech}},
year=2010,
booktitle={Proc. Speech Prosody 2010},
pages={paper 218}
}