REPORT ON SESSION I: PROSODIC AIDS TO SPEECH RECOGNITION 
Chair: Lynette Hirschman 
Four papers were presented in the opening session of the conference. 
The papers were "Prosody and Parsing" by P.J. Price (SRI), M. Ostendorf (Bos- 
ton University), and C.W. Wightman (Boston University), "Timing Models for 
Prosody and Cross-word Coarticulation in Connected Speech" by M. Beckman 
(Ohio State University), "Intonational Meaning in the Interpretation of 
Discourse," by J. Hirschberg (AT&T Bell Laboratories), and "Structure and 
Intonation in Spoken Language Systems," by M. Steedman (University of 
Pennsylvania). Price et al. reported on the use of prosodic information to 
resolve several types of syntactic ambiguities, the development of a prosodic 
information coding system suitable for a parser, and the development of 
automatic algorithms for extracting prosodic information. (Work jointly sup- 
ported by NSF and DARPA.) Mary Beckman reported on work in articulatory 
dynamics which suggests a new approach to the use of durational information 
in continuous speech recognition. New models of articulatory gesture allow for 
useful distinctions among the timing effects found in global tempo increase, 
phrase-final lengthening, and sentence accent. (Work supported by NSF.) Julia 
Hirschberg reported on work in empirical observation of the pragmatic uses of 
selected pitch contours. In addition, her report addressed the need for better 
speech data (goal-directed speech in a specific task domain) on which to test 
hypotheses about the interaction of prosodic constructs with the other com- 
ponents of a spoken language understanding system, particularly semantics and 
pragmatics. (Work supported by AT~T Bell Laboratories.) Mark Steedman 
reported on work in the description of intonational and syntactic structures in a 
combinatory extension of categorlal grammar. Combinatory categorial gram- 
mar predicts syntactic units which align with boundaries in the intonational 
structure, thus helping to clarify the structure of an utterance for spoken 
language understanding. (Work supported by DARPA and NSF.) 
