The Effects of Interaction on Spoken Discourse

THE EFFECTS OF INTERACTION ON SPOKEN DISCOURSE Sharon L. Oviatt Philip It. Cohen Artificial Intelligence Center SItI International 333 Ravenswood Avenue Menlo Park, California 94025-3493 ABSTRACT Near-term spoken language systems will likely be limited in their interactive capabilities. To design them, we shall need to model how the presence or absence of speaker interaction in- fluences spoken discourse patterns in different types of tasks. In this research, a comprehensive examination is provided of the discourse struc- ture and performance efficiency of both interac- tive and noninteractive spontaneous speech in a seriated assembly task. More specifically, tele- phone dialogues and audiotape monologues are compared, which represent opposites in terms of the opportunity for confirmation feedback and clarification subdialognes. Keyboard communi- cation patterns, upon which most natural lan- guage heuristics and algorithms have been based, also are contrasted with patterns observed in the two speech modalities. Finally, implications are discussed for the design of near-term limited- interaction spoken language systems. INTRODUCTION Many basic issues need to be addresssed be- fore technology will be able to leverage suc- cessfully from the natural advantages of speech. First, spoken interfaces will need to be struc- tured to reflect the realities of speech instead of text. Historically, language norms have been based on written modalities, even though spo- ken and written communication differ in major ways (Chafe, 1982; Chapanis, Parrish, Ochsman, & Weeks, 1977). Furthermore, it has become clear that the algorithms and heuristics needed to design spoken language systems will be different from those required for keyboard system s (Co- hen, 1984; Hindle, 1983; Oviatt & Cohen, 1988 ~: 1989; Ward, 1989). Among other things, speech understanding systems tend to have considerable difficulty with the indirection, confirmations and reaffirmations, nonword fillers, false starts and overall wordiness of human speech (van Katwijk, van Nes, Bunt, Muller & Leopold, 1979). To date, however, research has not yet provided ac- curate models of spoken language to serve as a basis for designing future spoken language sys- tems. People experience speech as a very rapid, direct, and tightly interactive communication modality, one that is governed by an array of conversational rules and is rewarding in its so- cial effectiveness. Although a full. y interactive ex- change that includes confirmatory feedback and clarification subdialo~mes is the prototypical or netural form of speech, near-term spoken lan- guage systems are likely to provide only limited interactive capabilities. For example, lack of ad- equate confirmatory feedback, variable delays in interactive processing, and limited prosodic anal- ysis all can be expected to constrain interactions with initial systems. Other speech technology, such as voice mail and automatic dictation de- vices (Gould, Conti & Hovanyecz, 1983; Jelinek, 1985), isdesigned specifically for noninteractive speech input. Therefore, to the extent that inter- active and noninteractive spoken language differ, future SLSs may require tailoring to handle phe- nomena typical of noninteractive speech. That is, at least for the near term, the goal of design- ing SLSs based on models of fully interactive di- alogne may be inappropriate. Instead, building …

Content truncated to 500 words