The Effects of Service Availability and Recognition Errors on Trust in Voice User Interfaces

Abstract

This study was conducted to determine the effects of speech recognition accuracy and system availability on customers' perceptions of a speech-enabled Interactive Voice Response (IVR) system. Fifty-six participants searched for bank rate information using a prototype speech recognition banking system in one of four conditions: (1) perfect system performance when obtaining rate information, (2) occasional speech recognition errors, (3) occasional loss of system availability, and (4) a combination of recognition errors and loss of system availability. A “system trust” measure was a better discriminator between conditions than a commonly-used subjective satisfaction measure: participants who experienced periods of unavailable service trusted the system less than those who experienced fully available service, but these groups reported similar subjective satisfaction rates. Participants who encountered speech recognition errors reported no lower levels of trust or satisfaction than those who experienced perfect recognition accuracy. The paper discusses the relationship between system trust and the willingness to use self-service systems, as well as special aspects of speech recognition systems in terms of “persona” and users' perceptions.

Get full access to this article

View all access options for this article.

References

Balentine

Morgan

D.P.

(2001). How to build a speech recognition application (2nd Ed.). San Ramon, CA: EIG Press.

Cohen

M.H

Giangola

J.P.

Balogh

(2004). Voice user interface design. New York: Addison-Wesley.

Hart

S.G.

Staveland

L.E.

(1987). Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. In Hancock

P.A.

Meshkati

(Eds.) Human mental workload. Amsterdam: Elsevier.

Jian

J-Y.

Bisantz

A.M.

Drury

C.G.

(1998). Towards an empirically determined scale of trust in computerized systems: Distinguishing concepts and types of trust. In Proceedings of the Human Factors & Ergonomics Society 42nd Annual Meeting, 501-505. Santa Monica, CA: HFES.

Jian

J-Y.

Bisantz

A.M.

Drury

C.G.

(2000). Foundations for an empirically determined scale of trust in automated systems International Journal of Cognitive Ergonomics, 4, 1, 53–71.

Lee

J.D.

See

K.A.

(2004). Trust in automation: Designing for appropriate reliance Human Factors, 46, 50–80.

Lewis

J.R.

(2002). Psychometric evaluation of the PSSUQ using data from five years of usability studies International Journal of Human-Computer Interaction, 14, 463–488.

MacDonald

A.P.

Kessel

V.S.

Fuller

J.B.

(1972). Self-disclosure and two kinds of trust Psychological Reports, 30, 143–148.

Peissner

Heidmann

Zeigler

(2001). Simulating recognition errors in speech user interface prototyping In Smith

M.J.

(Eds.). Usability evaluation and interface design (pp. 233–237). Lawrence Erlbaum: Mahwah, NJ.

10.

Rotter

J.B.

(1967). A new scale for the measurement of interpersonal trust Journal of Personality, 35, 651–665.

11.

Safar

J.A.

Turner

C.W.

(2005). Validation of a two factor structure for system trust. In Proceedings of the Human Factors & Ergonomics Society 49thAnnual Meeting. Orlando, FL: HFES.

12.

Terry

(2003). Will consumers use speech? Speech Technology Magazine, 8, 16–19. Available at http://www.speechtechmag.com/issues/8_1/cover/1591-1.html.

13.

Turner

C.W.

(2002). The online experience and consumers' perceptions of e-commerce security. In Proceedings of the Human Factors & Ergonomics Society 46thAnnual Meeting, (pp. 1246–1250). Baltimore, MD: HFES.