Composing Letters with a SimulatedListening TypewriterJOHN D. GOULD, JOHN CONTI and TODD HOVANYECZIBM Research Center
Writing vs Dictating• Evaluation of a Simulated Listening Typewriter.• 1983…• Aim of the experiments was to determine if an imperfectlistening typewriter would be useful for composing letters.
Simulated Listening Typewriter"Wizard of Oz" (Kelley, 1985) or "PNAMBIC"(Pay No Attention to the Man Behind theCurtain) (Bernstein, 1987) simulation.
The experiments 2 experiments 10 naive participants (10 assignments each) and 8 professionals (7assignments each). 1000, 5000 and unlimited vocabulary. Isolated and continuous speech. 2 strategies (draft and final). Written letters were included.
Methods of the experiments1. Observing (video logging)2. Asking users (preferences, opinions, …)3. Asking experts (evaluation of the produced letters)4. Testing (time measuring, error counting, …)
Conclusion• Some versions were as good as traditional methods ofhandwriting and dictating.• Isolated word speech + large vocabularies = a (potentially) usefullistening typewriter.• Some participants (especially of the second group) had beenfrustrated by the slow speed of the simulated listeningtypewriter.
A critic view• Speech recognition was under development (1983).• What about “ehs…”, “ums…” etc?• The text’s style (spacing, text orientation, …)?• Complex and time spending instructions.• Using of written notes was allowed (ambiguous ?).• Evaluation for disabled people.