Spontaneous speech is less of an option because of its
variability, which could make things difficult for a machine learning
algorithm.
(* On a more personal note, I'd like to hear from anybody who's
worked on clustering F0 contours (+ other assorted information)
or classifying prosody according to dialogue act. *)
Cheers,
Maria Wolters
mwo@asl1.ikp.uni-bonn.de