Identifying whether an utterance is a statement, question, greeting, and so forth is integral to effective automatic understanding of natural dialog. Little is known, however, about how such dialog acts (DAs) can be automatically classified in truly natural conversation. This study asks whether current approaches, which use mainly word information, could be improved by adding prosodic information. The study is based on more than 1000 conversations from the Switchboard corpus. DAs were handannotated, and prosodic features (duration, pause, F0, energy, and speaking rate) were automatically extracted for each DA. In training, decision trees based on these features were inferred

Researchers in Computer Supported Cooperative Work have recently developed discount evaluation methods for shared-workspace groupware. Most discount methods rely on some understanding of the context in which the groupware systems will be used, which means that evaluators need to model the tasks that groups will perform. However, existing task analysis schemes are not well suited to the needs of groupware evaluation: they either do not deal with collaboration issues, do not use an appropriate level of analysis for concrete assessment of usability in interfaces, or do not adequately represent the variability inherent in group work. To fill this gap, we have developed a new modeling technique called Collaboration Usability Analysis. CUA focuses on the teamwork that goes on in a group task rather than the taskwork. To enable closer links between the task representation and the groupware interface, CUA grounds each collaborative action in a set of group work primitives called the mechanics of collaboration. To represent the range of ways that a group task can be carried out, CUA allows variable paths through the execution of a task, and allows alternate paths and optional tasks to be modeled. CUA’s main contribution is to provide evaluators with a framework in which they can simulate the realistic use of a groupware system

A significant problem with telephone communication is that callers do not have enough awareness about the Personal Presence of people they want to call. The result can be unwanted, interrupting calls. The live addressbook is an application that helps users make more informed telephone calls and teleconferences, from anywhere, via their wireless PDA or desktop browser. Unlike other network-based address books, which maintain static information, the live addressbook can display dynamic information about where the recipient currently is (i.e., reach number), and how available he/she currently is for calls. The system accomplishes this by applying to telephony the “Buddy List ” concepts made popular in Instant Messaging applications. User trials assess the applicability of Personal Presence information in a telephone context.

This article is a substantially expanded version of a report presented at the 1998 ACM CHI conference [Gutwin and Greenberg 1998]. Authors' addresses: C. Gutwin, Department of Computer Science, University of Saskatchewan, 57 Campus Drive, Saskatoon, Saskatchewan S7N 5A9, Canada; email: gutwin@cs.usask.ca; S. Greenberg, Department of Computer Science, University of Calgary, 2500 University Drive NW, Calgary, Alberta T2N 1N4, Canada; email: saul@cpsc.ucalgary.ca. Permission to make digital / hard copy of part or all of this work for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage, the copyright notice, the title of the publication, and its date appear, and notice is given that copying is by permission of the ACM, Inc. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and / or a fee

Face Transfer is a method for mapping videorecorded performances of one individual to facial animations of another. It extracts visemes (speech-related mouth articulations), expressions, and three-dimensional (3D) pose from monocular video or film footage. These parameters are then used to generate and drive a detailed 3D textured face mesh for a target identity, which can be seamlessly rendered back into target footage. The underlying face model automatically adjusts for how the target performs facial expressions and visemes. The performance data can be easily edited to change the visemes, expressions, pose, or even the identity of the target—the attributes are separably controllable. This supports

We describe representation, inference strategies, and control procedures employed in an automated conversation system named the Bayesian Receptionist. The prototype is focused on the domain of dialog about goals typically handled by receptionists at the front desks of buildings on the Microsoft corporate campus. The system employs a set of Bayesian user models to interpret the goals of speakers given evidence gleaned from a natural language parse of their utterances. Beyond linguistic features, the domain models take into consideration contextual evidence, including visual findings. We discuss key principles of conversational actions under uncertainty and the overall architecture of the system, highlighting the use of a hierarchy of Bayesian models at different levels of detail, the use of value of information to control question asking, and application of expected utility to control progression and backtracking in conversation.

www.cs.usask.ca/faculty/gutwin Collaboration in current real-time groupware systems is often an awkward and clumsy process. We hypothesize that better support for workspace awareness can improve the usability of these shared computational workspaces. We conducted an experiment that compared people’s performance on two versions of a groupware interface. The interfaces used workspace miniatures to provide different levels of support for workspace awareness. The basic miniature showed information only about the local user, and the enhanced miniature showed the location and activity of others in the workspace as well. In two of three task types tested, completion times were lower with increased awareness support, and in one task type, communication was more efficient. Participants also greatly preferred the awareness-enhanced system. The study provides empirical evidence of, and underlying reasons for, the value of supporting workspace awareness in groupware.

At first glance it seems absurd that busy people doing important jobs should want their computers to interrupt them. Interruptions are disruptive and people need to concentrate to make good decisions. However, successful job performance also frequently depends on people's abilities to (a) constantly monitor their dynamically changing information environments, (b) collaborate and communicate with other people in the system, and (c) supervise background autonomous services. These critical abilities can require people to simultaneously query a large set of information sources, continuously monitor for important events, and respond to and communicate with other human operators. Automated monitoring

People working collaboratively must establish and maintain awareness of one another's intentions, actions and results. Notification systems typically support awareness of the presence, tasks and actions of collaborators, but they do not adequately support awareness of persistent and complex activities. We analysed awareness breakdowns in use of our Virtual School system---stemming from problems related to the collaborative situation, group, task and tool support---to motivate the concept of activity awareness. Activity a areness builds on prior conceptions of social and action a areness, but emphasizes the importance of activity context factors like planning and coordination. This ork suggests design strategies for notification systems to better support collaborative activity.

The development of context-aware applications will require tools that are based on clearly defined models of context and system software architecture. This essay introduces models for each of these, examines the tradeoffs among the different alternatives, and describes a blackboard-based context architecture that is being used in the construction of interactive workspaces. 1.