The automatic reading of books by text-to-speech synthesizers requires not only the
adequate encoding of the many levels of information and
discourse structures by acoustic signals but also the proper patterns of breathing, so
that to pace information and organize discourse at an ecological
We analyze here the locations and durations of more than 2000 pauses produced by voice donor who has read several audiobooks, freely available via the litteratureaudio.com website. Since the voice was recorded by a close microphone, we also characterized the acoustic markers of inhalation and show that the delay between end of phonation and air intake can be considered an additional marker of thematic continuity between the two adjacent speech chunks that complements well-documented prosodic cues such as the preboundary tone or the pause duration.
Index Terms: prosody, pause, respiration, prediction of pause locations and durations
Bibliographic reference. Bailly, Gérard / Gouvernayre, Cécilia (2012): "Pauses and respiratory markers of the structure of book reading", In INTERSPEECH-2012, 2218-2221.