Interactive Voice Response Units (IVRUs) answer the phones more often than people do in many business domains, including Telecommunication, Personal Finance, Utilities, etc. This paper presents the results of a research study that Sprint initiated to solve a specific business problem within its IVRU. Two design approaches were assessed, pitting a Natural Language with Directed Dialog Fallback structure versus a traditional Directed Dialog framework. Key measurements included task completion and efficiency. The Natural Language with Directed Dialog Fallback design slightly outperformed the Directed Dialog approach by providing a compelling hybrid of two archetypal IVRU approaches.
Get full access to this article
View all access options for this article.
References
1.
GorinA.L.ParkerB.A.SachsR.M.SachsJ.G.Wilpon How May I Help You? In Proceedings of Interactive Voice Technology for Telecommunications Applications (Basking Ridge, NJ: Sep 30- Oct 1) IEEE Piscataway, NJ pp. 57–60.
2.
BlanchardH. E.StewartO. T., Conversational Re-Prompting In Natural Language Dialog, Proceedings of the Human Factors and Ergonomics Society 48th Annual Meeting-2004, New Orleans, Louisiana. pp. 708–711.
3.
VincentW.VanhouckeLawrenceNeeleyMariaMortatiMichaelSloanJ.NassClifford. “Effects of Prompt Style when Navigating through Structured Data” (with accompanying presentation Speech and Search). Proceedings of INTERACT 2001, Eighth IFIP TC.13 Conference on Human Computer Interaction (IOS Press), pp.530–536, Tokyo, Japan, 2001.
4.
WilliamsJason D.WittSilke M.. A Comparison of Dialog Strategies for Call Routing. International Journal of Speech Technology (Vol 7, No 1). January 2004, pp 9–24.
5.
GorinA.L.RiccardiG.RiccardiJ.H.Wright How May I Help You?Speech Communication, vol. 23, pp. 113–127, 1997.
6.
SuhmB.BersJ.McCarthyD.FreemanB.GettyD.GodfreyK.PetersonP.“A Comparative Study of Speech in the Call Center: Natural Language Call Routing vs. Touch-Tone Menus,” CHI 2002, April 20-25, 2002, Minneapolis, Minnesota, USA pp. 283–290.
7.
BoyceS., Natural Spoken Dialogue Systems for Telephony Applications, September 2000/Vol. 43, No. 9 Communications of the ACM pp. 29–34.
8.
DahlbackN.JonssonA.AhrenbergL., (1993) Wizard of Oz studies — Why and How, Proceedings of Intelligent User Interfaces 1993 pp. 193–200.
9.
McInnesF RNairnI AAttwaterD JJackM A, “Effects of prompt style on user responses to an automated banking service using word-spotting”, BT Technical JournalVol 17, No 1 January 1999.
