Despite its widespread use, voicemail presents numerous usability challenges: People must listen to messages in their entirety, they cannot search by keywords, and audio files do not naturally support visual skimming. SCANMail overcomes these flaws by automatically generating text transcripts of voicemail messages and presenting them in an email-like interface. Transcripts facilitate quick browsing and permanent archive. However, errors from the automatic speech recognition (ASR) hinder the usefulness of the transcripts. The work presented here specifically addresses these problems by evaluating user-initiated error correction of transcripts. User studies of two editor interfaces-a grammar-assisted menu and simple replacement by typing-reveal reduced audio playback times and an emphasis on editing important words with the menu, suggesting its value in mobile environments where limited input capabilities are the norm and user privacy is essential. The study also adds to the scarce body of work on ASR confidence shading, suggesting that shading may be more helpful than previously reported.

Classroom BRIDGE supports activity awareness by facilitating planning and goal revision in collaborative, project-based middle school science. It integrates large-screen and desktop views of project times to support incidental creation of awareness information through routine document transactions, integrated presentation of awareness information as part of workspace views, and public access to subgroup activity. It demonstrates and develops an object replication approach to integrating synchronous and asynchronous distributed work for a platform incorporating both desktop and large-screen devices. This paper describes an implementation of these concepts with preliminary evaluation data, using timeline-based user interfaces.

Increasing amounts of public, corporate, and private speech data are now available on-line. These are limited in their usefulness, however, by the lack of tools to permit their browsing and search. The goal of our research is to provide tools to overcome the inherent difficulties of speech access, by supporting visual scanning, search, and information extraction. We describe a novel principle for the design of UIs to speech data: What You See Is Almost What You Hear (WYSIAWYH). In WYSIAWYH, automatic speech recognition (ASR) generates a transcript of the speech data. The transcript is then used as a visual analogue to that underlying data. A graphical user interface allows users to visually scan, read, annotate and search these transcripts. Users can also use the transcript to access and play specific regions of the underlying message. We first summarize previous studies of voicemail usage that motivated the WYSIAWYH principle, and describe a voicemail UI, SCANMail, that embodies WYSIAWYH. We report on a laboratory experiment and a two-month field trial evaluation. SCANMail outperformed a state of the art voicemail system on core voicemail tasks. This was attributable to SCANMail's support for visual scanning, search and information extraction. While the ASR transcripts contain errors, they nevertheless improve the efficiency of voicemail processing. Transcripts either provide enough information for users to extract key points or to navigate to important regions of the underlying speech, which they can then play directly

Increasing amounts of public, corporate, and private audio data are available for use, but limited in usefulness by the lack of tools to permit their browsing and search. In this paper, we describe SCANMail, a system that employs automatic speech recognition, information retrieval, information extraction, and human computer interaction technology to permit users to browse and search their voicemail messages by content through a graphical user interface interface. The SCANMail client also provides note-taking capabilities as well as browsing and querying features. A CallerId server also proposes caller names from existing caller acoustic models and is trained from user feedback. An Email server sends the original message plus its transcription to a mailing address specified in the user's profile. 1.

SCANMail is a prototype system developed at AT&T Labs for the purpose of providing useful tools for managing and searching through voicemail messages. Content is extracted from voicemail messages using various speech and text processing tools. One such content category is the identity of the message caller. This paper describes CallerID, the server tool attached to SCANMail for the purpose of providing caller labels for voicemail messages. CallerID make use of text independent speaker recognition techniques. Two kinds of requests are handled by the CallerID server. A request triggered by the arrival of a new voicemail message results in the processing of the message to score it against the models of callers assigned to the user (recipient) in order to propose the identity of the caller. A second request is initiated by a user who provides a caller label for a message he/she has reviewed. CallerID processes the message and uses it to train or adapt a speaker model for the caller whose label is provided. The paper describes in detail the CallerID functions and provides some results of performance evaluations of the caller identification capability.

The World Wide Web has served as a medium for collaboration since its inception. Web-based collaboration has, however, been dominated by systems supporting asynchronous activities such as sharing documents and participating in discussion forums. Supporting interactive, synchronous collaboration on the Web has proven much more challenging. In this paper we describe three of the challenges encountered in the context of supporting network-based collaboration among middle and high school science students: integrating synchronous and asynchronous modes of interaction, minimizing consumption of bandwidth, and adapting non-collaborative software components for collaborative use. We then present the Content Object Replication Kit, a toolkit for building interactive Java-based collaborative systems for use on the Web.