EUROSPEECH 2003 - INTERSPEECH 2003
In this paper, we explore a text type based scheme of text analysis, through the specific problem of detecting the list text type. This is important because TTS systems that can generate the very distinct F_0 contour of lists sound more natural. The presented list detection algorithm uses part-of-speech tags as input, and detects lists by computing the alignment costs of clauses in a sentence. The algorithm detects lists with 80% accuracy.
Bibliographic reference. Mishra, Taniya / Klabbers, Esther / Santen, Jan P.H. van (2003): "Detection of list-type sentences", In EUROSPEECH-2003, 2477-2480.