Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Coupling Dialogue and Prosody Computation in Spoken Dialogue Generation

Christine H. Nakatani (1), Jennifer Chu-Carroll (2)

(1) Dialog R&D, Nuance Communications, Menlo Park, CA, USA
(2) Bell Labs, Lucent Technologies, Murray Hill, NJ, USA

We introduce a concept-to-speech (CTS) system that generates prosodic structure compositionally, in a spoken dialogue agent architecture. Representations from the semantic interpretation, task modeling, and dialogue strategy selection components drive the computation of accentuation, pitch accent type selection, and choice of melodic contour, respectively. These principled couplings of dialogue and prosody computation extend both the theory and practice of concept-to-speech generation.


Full Paper

Bibliographic reference.  Nakatani, Christine H. / Chu-Carroll, Jennifer (2000): "Coupling dialogue and prosody computation in spoken dialogue generation", In ICSLP-2000, vol.2, 415-418.