Despite the ready availability of digital recording technology and the continually decreasing cost of digital storage, browsing audio recordings remains a tedious task. This paper presents evidence in support of a system designed to assist with information comprehension and retrieval tasks from a large collection of recorded speech. Two techniques are employed to assist users with these tasks. First, a speech recognizer creates necessarily error-laden transcripts of the recorded speech. Second, audio playback is time-compressed using the SOLAFS technique. When used together, subjects are able to perform comprehension tasks with more speed and accuracy.

Article Free Access Share on Meme tags and community mirrors: moving from conferences to collaboration Authors: Richard Borovoy MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile , Fred Martin MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile , Sunil Vemuri MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile , Mitchel Resnick MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile , Brian Silverman MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile , Chris Hancock MIT Media Laboratory, 20 Ames Street, Cambridge, MA MIT Media Laboratory, 20 Ames Street, Cambridge, MAView Profile Authors Info & Claims CSCW '98: Proceedings of the 1998 ACM conference on Computer supported cooperative workNovember 1998 Pages 159–168https://doi.org/10.1145/289444.289490Online:01 November 1998Publication History 112citation991DownloadsMetricsTotal Citations112Total Downloads991Last 12 Months46Last 6 weeks10 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

Virtual documents are hypermedia documents that are generated on demand in response to reader input. This paper describes a virtual document application that generates natural language explanations about the structure and behavior of electromechanical systems. The application, called DME, structures the interaction with the reader as a question–answer dialog. Each page of the hyperdocument is the answer to a question, and each link on each page is a follow-up question that leads to another answer. DME is a model-based virtual document generator; unlike conventional database front-ends that provide views onto data, DME dynamically constructs the document's content (i.e. coherent explanations in English) from underlying mathematical and symbolic models. DME-based virtual documents have been running on the WWW since late 1993. They are used to document engineered systems in support of collaborative design and simulation-based training. In this paper we describe and demonstrate the DME application (with examples that run), and describe how it generates virtual documents on the web. We discuss the impact that model-based virtual documentation can have on the way technical documentation is authored and delivered.