Technical reports

Efficient computer interfaces using continuous gestures, language models, and speech

Keith Vertanen

March 2005, 46 pages

This technical report is based on a dissertation submitted July 2004 by the author for the degree of Master of Philosophy (Computer Speech, Text and Internet Technology) to the University of Cambridge, Darwin College.

Abstract

Despite advances in speech recognition technology, users of dictation systems still face a significant amount of work to correct errors made by the recognizer. The goal of this work is to investigate the use of a continuous gesture-based data entry interface to provide an efficient and fun way for users to correct recognition errors. Towards this goal, techniques are investigated which expand a recognizer’s results to help cover recognition errors. Additionally, models are developed which utilize a speech recognizer’s n-best list to build letter-based language models.

Full text

PDF (0.6 MB)

BibTeX record

@TechReport{UCAM-CL-TR-627,
  author =	 {Vertanen, Keith},
  title = 	 {{Efficient computer interfaces using continuous gestures,
         	   language models, and speech}},
  year = 	 2005,
  month = 	 mar,
  url = 	 {http://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-627.pdf},
  institution =  {University of Cambridge, Computer Laboratory},
  number = 	 {UCAM-CL-TR-627}
}