Interacting with SpeechSkimmer
Barry Arons,
Speech Interaction Research
E-mail: barons@mailhub.media.mit.edu
SpeechSkimmer is an interactive system for quickly browsing and finding
information in speech recordings. Skimming speech recordings is much more
difficult than visually scanning images, text, or video because of the
slow, linear, temporal nature of the audio channel. The SpeechSkimmer
system uses a combination of (1) time compression and pause removal, (2)
automatically finding segments that summarize a recording, and (3)
interaction techniques, to enable a speech recording to be heard quickly
and at several levels of detail.
SpeechSkimmer was first presented at UIST '93. Since that time several
important features have been added. Most notable is the use of a
pitch-based emphasis detection algorithm to automatically find topic
introductions and summarizing statements from a recording. This
demonstration is presented as a hands-on guide, allowing one to explore the
SpeechSkimmer user interface.
Back to the advance program
Back to UIST '95 home page