Use of speech technology in real life environment

  • Authors:

  • Ruimin Hu;Shaojian Zhu;Jinjuan Feng;Andrew Sears

  • Affiliations:

  • Computer and Information Sciences Department, Towson University, Towson, MD;Department of Information Systems, Interactive Systems Research Center, UMBC, Baltimore, MD;Computer and Information Sciences Department, Towson University, Towson, MD;Department of Information Systems, Interactive Systems Research Center, UMBC, Baltimore, MD

  • Venue:
  • UAHCI'11 Proceedings of the 6th international conference on Universal access in human-computer interaction: applications and services - Volume Part IV
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper reports results from two six-month field studies investigating the use of speech-based interactions in real world environments. The first study focused on the use of speech-based dictation/word processing tasks that allow users to generate text such as reports or emails. The second study took a broader view and examined two types of interactions: speech-based dictation for word processing and speech-based command and control supporting interactions with the graphical user interface. The results suggest that user requirements for speech-based interactions have evolved as the technology matured to include better support for formatting text documents as well as more effective support for other applications. While significant research has focused on the use of speech recognition to generate text, our participants spent substantially more time using speech recognition for other, often unexpected tasks such as instant messaging and web browsing. The use of speech recognition to support informal communication is particularly interesting as accuracy may be less critical in this context. Further research is needed to address these emerging requirements for speech technologies.