7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Choosing Speech or Touchtone Modality for Navigation within a Telephony Natural Language System

Jennifer C. Lai (1), Kwan Min Lee (2)

(1) IBM T.J. Watson Research Center, USA; (2) University of Southern California, USA

In this paper, we describe the empirical findings from a user study (N=16) that compares the use of touchtone and speech modalities to navigate within a telephone-based message retrieval system. Unlike previous studies comparing these two modalities, the speech system used was a working natural language system. Results indicate that a majority of users preferred interacting by speech even though the touchtone interface was more efficient as measured by the success rate and speed for each task. The interaction with the speech modality was rated as being more satisfying, more entertaining, and more natural than the touchtone modality. This is an interesting demonstration of how user satisfaction may not always correspond completely with efficiency measures in task-based scenarios. The findings underline the importance of examining speech interfaces from other perspectives in addition to efficiency maximization. The paper also describes a speech- based telephony application, which is used for access to unified messaging (email, voicemail, and faxes) and calendar information. The application is currently deployed at IBM Research and in use by more than 200 users.


Full Paper

Bibliographic reference.  Lai, Jennifer C. / Lee, Kwan Min (2002): "Choosing speech or touchtone modality for navigation within a telephony natural language system", In ICSLP-2002, 1509-1512.