Dealing with system response times in interactive speech applications

ABSTRACT

In this user study, we address several open issues in the design of waiting cues for system response time (SRT) in interactive telephony speech applications. User observations and structured preference tests indicate that silent waiting times should not be longer than 4 -- 8 seconds. Already at short durations, music combined with speech was favored to silence. A preference test regarding several non-speech waiting cues proposed in literature suggests that music is preferred to more simple synthetic sounds and to natural sounds. The continuous indication of the remaining waiting time by speech was rated as much more pleasant and appropriate than a non-speech audio progress meter. Commercial announcements and navigational advice during waiting times were not accepted by the subjects. Empirically based guidelines for a maximum waiting duration in voice services is given. Implications for the design of auditory waiting cues for SRT are discussed.

REFERENCES

• 1: Balentine, B, and Morgan, D. How to Build a Speech Recognition Application: A Style Guide for Telephony Dialogues. San Ramon, CA, Enterprise Integration Group. 2004.
• 2: Michael H. Cohen , James P. Giangola , Jennifer Balogh, Voice User Interface Design, Addison Wesley Longman Publishing Co., Inc., Redwood City, CA, 2004
• 3: Crease, M.G. and Brewster, S.A. Making Progress With Sounds - The Design and Evaluation Of An Audio Progress Bar. Proc. of ICAD'98, British Computer Society (1998).
• 4: Larson, J. The voice XML Guide, Lesson 12: Resource Management. http://www.larson-tech.com/U12/12.html
• 5: Brad A. Myers, The importance of percent-done progress indicators for computer-human interfaces, Proceedings of the SIGCHI conference on Human factors in computing systems, p.11-17, April 1985, San Francisco, California, United States
• 6: Jakob Nielsen, Usability Engineering, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 7: Polkosky, M.D. User preference for system processing tones (Tech. Rep. No. 29.3436). Raleigh, NC: IBM, 2001.
• 8: Polkosky, M.D., Lewis, J.R. Effect of Auditory Waiting Cues on Time Estimation in Speech Recognition Telephony Applications. International Journal of Human-Computer Interaction, 14, 3-4 (2002), 275--278.
• 9: VoiceAward 2004, http://www.voiceaward.de/
• 10: Von Niman, B. Mobile Communication: Simplifying the Complexity, Business Briefings: Wireless Technology (2004). www.bbriefings.com

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)

Additional Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.3 Communications Applications

Keywords:
auditory I/O and sound in the UI, mobile communication, speech I/O, system response time, user preference