translate

Speech Dasher

A square image divided into three uneven colored blocks with a red frequency line running through the middle and the lowercase letters a and b at the top and bottom.
Product Type: 
Device modifier
Manufacturer Name: 
Keith Vertanen
Find products similar to this onesimilar_products_button

Product Description: 

Speech Dasher is a free text entry interface in which users first speak their desired text and then use the zooming interface Dasher to confirm and correct the recognition result.

Main Features: 

  • Entering text using Speech Dasher begins with the user speaking their desired sentence to a continuous speech recognition engine.
  • A word lattice is generated from the recognizer’s results and then expanded to cover likely recognition errors.
  • The expanded lattice is used to estimate the probability of what letter the user might enter next based on both the recognition results and what has already been entered.
  • The interface also integrates a default language model, allowing the user to enter words missed completely by the recognizer.
  • These probability estimates are then used in the continuous gestured-based interface Dasher to allow the user to confirm and correct their dictated sentence.
  • After several hours of practice, users wrote using Speech Dasher at 40 (corrected) words per minute.
  • Users did this using only speech and the direction of their gaze (obtained via an eye tracker).
  • Despite an initial recognition word error rate of 22%, users corrected virtually all recognition errors.

Primary Specifications: 

  • Runs on Microsoft Windows.

More Information: 

This product is a freeware software available for free download off of the internet from Keith Vertanen or search for: “open source freeware Speech Dasher”.