@inbook{3b9304e5e3b948cdb5f002112e68e833,
title = "Prosodic Processing",
abstract = "Speech synthesis speechsynthesis systems have to generate natural-sounding speech output from text. One of the key aspects of speech is prosodic processing prosody, which must be both natural (i.e., sounding like a human) and meaningful (i.e., sounding like a human who understands the contents of the text). The computation of prosody from text can be divided into the computation of prosodic tags from text and the computation of acoustic speech features from these tags. This chapter focuses on the latter. It provides an overview of prosody in human-human communication, including the communicative functions of prosody and the acoustic correlates. Discussed next is a historical overview of the various methods that have been used for prosody generation in speech synthesis, as well as of current methods. Special attention is paid to prosody generation in unit selection synthesis methods, in which large corpora are searched for fragments of speech that match the phonemes and prosodic tags computed from text and that optimize various cost functions, and in which prosody is not modeled and speech not modified. We conclude the chapter by advocating hybrid approaches in which search capabilities of unit selection methods are combined with the speech modification methods from more-traditional approaches.",
keywords = "Intonational Phrase, Pitch Accent, Pitch Contour, Speech Synthesis System, Unit Selection",
author = "{van Santen}, Jan and Taniya Mishra and Esther Klabbers",
note = "Publisher Copyright: {\textcopyright} 2008, Springer-Verlag Berlin Heidelberg.",
year = "2008",
doi = "10.1007/978-3-540-49127-9_23",
language = "English (US)",
series = "Springer Handbooks",
publisher = "Springer",
pages = "471--488",
booktitle = "Springer Handbooks",
}