This research characterizes the spontaneous spoken disfluencies typical of human-computer interaction, and presents a predictive model accounting for their occurrence. Data were collected during three empirical studies in which people spoke or wrote to a highly interactive simulated system as they completed service transactions. The studies involved within-subject factorial designs in which the input modality and presentation format were varied. Spoken disfluency rates during human-computer interaction were documented to be substantially lower than rates typically observed during comparable human-human speech. Two separate factors, both associated with increased planning demands, were statistically related to higher disfluency rates: (1) length of utterance, and (2) lack of structure in the presentation format. Regression techniques demonstrated that a linear model based simply on utterance length accounted for over 77% of the variability in spoken disfluencies. Therefore, design methods ca...

this paper is to develop an alternative proposal whereby long-distance agreement is brokered via a correspondence-theoretic relation established between the participant segments. We term this approach Long-Distance Agreement through Correspondence or LDAC. A chief assertion of the LDAC proposal is that agreement is determined by Identity constraints which check feature matching in corresponding consonants, thereby obviating representations in which feature linkage skips over spans of neutral segments. Another key claim is that similarity plays a decisive role in identifying which segments stand in correspondence

Abstract not found

Many existing natural language generation systems can be characterized according to their modularization as either pipelined or interleaved. In these separated systems, the generator is divided into several modules (e.g., planning and realization), with control and information passing between the modules during the generation process. This paper proposes a third type of generator, which we call integrated, that unifies the modules into a single mechanism. The mechanism uses a small set of orthogonal basic operations to produce planned and grammatical language output. Integrated systems are conceptually attractive and may support generation of pragmatic effects more effectively than other systems. After discussing the advantages of the integrated approach, we summarize GLINDA, an integrated generator currently under development at Carnegie Mellon. GLINDA is the generator used for narration and intercharacter communication in the Oz Interactive Fiction and Virtual Reality Project.

INTRODUCTION Psycholinguistic research into language production---the process of translating thoughts into speech---has long been associated with connectionist models. Spreading activation models of lexical access in production represent some of the earliest applications of connectionist ideas to psycholinguistic data (e.g., Dell & Reich, 1977; Harley, 1984; MacKay, 1982; Stemberger, 1985). These models combined representations from linguistics with interactive activation principles and sought to explain speech errors, particularly errors resulting from multiple causes or processing levels. For example, "Lizst's second Hungarian restaurant " instead of "rhapsody " involves mistakenly using a word that is associatively, syntactically, and phonologically related to the intended word. Activation that spreads interactively among processing levels seems to be a natural way to account for these kinds of slips. Direct all correspondence to: Gar

this report was submitted about how the processes are affected by fre- to fulfill the requirements for a Masters degree from the quency and constraint

this paper states that different levels of processing can work on different pieces of an utterance at the same time. Thus, the phonological encoder can work on the early part of the clause while the syntactic encoder works on filling out what remains. As a result, once the syntactic representation for the sentence is done, its corresponding phonological representation is likely close to complete as well. 29

Heavy-NP shift is the tendency for speakers to place long or "heavy" noun phrase direct objects at the end of a sentence rather than in the canonical post-verbal position. Three experiments using several task variations confirmed that length of the noun phrase influenced the ordering of the noun phrase and prepositional phrase during production. We also found that heavy-NP shift was strongly constrained by the "shifting disposition" of individual verbs. Verbs that do not require their complements (e.g., sentential complements) to appear in an adjacent position yielded more shifting during production than verbs that more frequently appear adjacent to their complements. Analyses of decision/preparation times suggested that shifted and unshifted structures competed for selection. These findings point to the simultaneous activation of lexically derived syntactic representations and ordering options in sentence planning. A multiple constraints framework provides a means of reconciling the e...

This paper links prosody to the information in the text and how it is processed by the speaker. It describes the operation and output of Loq, a text-to-speech implementation that includes a model of limited attention and working memory. Attentional limitations are key. Varying the attentional parameter in the simulations varies in turn what counts as given and new in a text, and therefore, the intonational contours with which it is uttered. Currently, the system produces prosody in three different styles: child-like, adult expressive, and knowledgeable. This prosody also exhibits differences within each style -- no two simulations are alike. The limited resource approach captures some of the stylistic and individual variety found in natural prosody. 1. INTRODUCTION Ask any lay person to imitate computer speech and you will be treated to an utterance delivered in melodic and rhythmic monotone, possibly accompanied by choppy articulation and a voice quality that is nasal and strained. ...

After reviewing situational and demographic factors that have been argued to affect speakers' disfluency rates, we examined disfluency rates in a corpus of task-oriented conversations(Schober & Carstensen, 2001) with variables that might affect fluency rates. These factors included: speakers' ages (young, middle-aged, and older), task roles(directorvs. matcher in a referentialcommunication task), difficulty of topic domain (abstract geometric figures vs. photographsof children),relationshipsbetween speakers(marriedvs. strangers), andgender(each pair consistedof a man anda woman).Older speakersproduced only slightly higher disfluency rates than young and middle-aged speakers. Overall, disfluency rates were higher both when speakers acted as directors and when they discussed abstract figures, confirming that disfluencies are associatedwith an increasein planningdifficulty. However, fillers(such as uh)were distributedsomewhat differentlythan repeatsor restarts, supportingthe idea that fillers may be a resourcefor or a consequence of interpersonal coordination.