15th International Congress of Phonetic Sciences (ICPhS-15)
Duration is a primary factor both to achieve more natural-sounding synthesis and as an indicator of phrasal organization in speech recognition. In this study, we investigate pauses and durational patterns in spontaneous conversation, as well as how reliably such elements can serve as boundary-marking predictors across different types of speech corpora. Our results show that pause duration is significantly correlated with specific boundary status and that syllable duration is inversely correlated with distance to phrase end, suggesting that syllable duration is very significant in predicting phrase boundary status. Our findings show that duration features are highly informative and that it is crucial to integrate such knowledge to enhance performance in spoken language systems.
Bibliographic reference. Yang, Li-chiung (2003): "Duration and pauses as phrasal and boundary marking indicators in speech", In ICPhS-15, 1791-1794.