We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speec-act-like

We describe a new approach for statistical modeling and detection of discourse structure for natural conversational speech. Our model is based on 42 `Dialog Acts' (DAs), (question, answer, backchannel, agreement, disagreement, apology, etc). We labeled 1155 conversations from the Switchboard (SWBD) database (Godfrey et al. 1992) of human-to-human telephone conversations with these 42 types and trained a Dialog Act detector based on three distinct knowledge sources: sequences of words which characterize a dialog act, prosodic features which characterize a dialog act, and a statistical Discourse Grammar. Our combined detector, although still in preliminary stages, already achieves a 65% Dialog Act detection rate based on acoustic waveforms, and 72% accuracy based on word transcripts. Using this detector to switch among the 42 dialog-act-specific trigram LMs also gave us an encouraging but not statistically significant reduction in SWBD word error. 1 Introduction The ability to model and...

The use of remote communication technologies to carry out daily work is becoming increasingly common, and their use in certain settings is already commonplace. Yet, in spite of the fact that significant sums are being spent on the acquisition of technologies to support distributed work, we are only beginning to understand the intricacies of these interactions. This paper identifies and analyzes one particular limitation of video-based teleconferencing, the impact of an audio and video delay on distributed communication. It offers a detailed microanalysis of one distributed team's use of videoconferencing to support remote teamwork. We explore through this analysis the impact which technology-generated delays may have on shared meaning-making between remote participants. We draw conclusions about the significance of our findings for understanding talk, interaction and collaboration across remote links, and conclude with recommendations for designers, users and implementers.

Dialogue has its origins in joint activities, which it serves to coordinate. Joint activities, in turn, usually emerge in hierarchically nested projects and subprojects. We propose that participants use dialogue to coordinate two kinds of transitions in these joint projects: vertical transitions, or entering and exiting joint projects; and horizontal transitions, or continuing within joint projects. The participants help signal these transitions with project markers, words such as uh-huh, m-hm, yeah, okay, or all right. These words have been studied mainly as signals of listener feedback (back-channel signals) or turn-taking devices (acknowledgment tokens). We present evidence from several types of well-defined tasks that they are also part of a system of contrasts specialized for navigating joint projects. Uh-huh, m-hm and yeah are used for horizontal transitions, and okay and all right for vertical transitions.

Conversation coordinates joint activities and the joint projects that compose them. Participants coordinate (1) vertical transitions on entering and exiting joint projects; and (2) horizontal transitions in continuing within them. Transitions are coordinated using project markers such as uh-huh, yeah, right, and okay. In the authors’ proposal, participants use uh-huh, yeah, and right to continue within joint projects, and okay and all right to enter and exit them. This was examined in 2 telephone conversation corpora. Telephone conversations divide into an entry, body, and exit phase, each of which is a joint project. Okay and all right were used to transit from the entry to body and from body to exit, whereas uh-huh, yeah, and right were used within the body. JOINT PROJECTS IN CONVERSATION In conversation, the participants do not just speak—they do things together. These joint actions are normally the reason for their encounter, and their talk is shaped by the need to coordinate them. To understand what people are doing in conversation, one must understand the joint activities they are engaged in. Outside of conversation, individual and joint activities have long been analyzed into hierarchies of projects and subprojects (Cranach, Kalbermatten, Indermühle,

The way in which communicative intentions are mapped to language is a central problem in linguistic theory. This paper discusses this issue it relates to a little studied phenomenon, namely non-lexical conversational sounds (conversational grunts). The analysis is based primarily on examination of a few hundred occurrences, including such items as uh-huh, un-hn. um, mm, and oh, in a corpus of American English conversations, Th--e datncldesxtenslv phonetic variation, suggesting that these items are best explained, not as fixed words, but as dynamic creations. In particular, the vast majority of these items can be generated by a simple mode] consisting of 10 component sounds and 2 combining rules. Moreover. each of these component sounds seems to bear some meanlng or function wlich is fairly constant across grunts and across contexts; and so the meanings of conversational grunts arelargely a product of sound symbolism. This analysis is compatible with acoustic and cognitive properties of the conversational contexts in which grunts occur.

Turn-taking is usually considered to follow a simple set of rules, enacted through a perhaps more complicated system of signals. The most significant aspect of the turn-taking process is that, in most cases, it proceeds in a very smooth fashion. Speakers signal to each other that they wish to either yield or take the turn through syntactic, pragmatic, and prosodic means. In this paper, I explore how the turn-taking process develops in two different sets of Spanish conversations. In the first group of conversations, speakers take turns spontaneously, presumably as they would do in everyday situations. In the second group, turns were mechanically controlled, and communication was one-way. A comparison of the two types of conversation provides insights into the signals used in spontaneous turn-taking.

this article. / 53 ( *Question: do we have examples responding to tag questions with 'nd' in our dabase? ) If e dispreferred pre-answer sequence is transcribed in the same slash unit as e 'no' answer, it is not coded. Rher, the answer itself is coded 'nn' as shown in this example: bf B.66 uttl: Okay. / B.66 utt2: {D So, ) [ [ you, + you were out of s-, ] + you went Here B stats a "disprefered response" sequence, (Well...) but then A changes the question allowing B to answer"yes"

this paper, I illustrate this by considering cases in which patients produce unsolicited turns at talk 1 while a prescription is being issued, either to raise issues concerning the prescription per se or to introduce unrelated topics (concerning, for example, other complaints, social issues, or problems encountered by members of their family). Subsequently, I discuss some of the potential design implications of the findings and suggest that the linkage between human-computer interaction and face-to-face interpersonal communication raises important issues for the field of HCI

Abstract not found