This paper introduces a new breed of natural language dialog applications which we refer to as the Help Desk. These voice-enabled applications are an evolution from Help Desk services that are currently available on the web or being supported by human agents. The goals of a voice-enabled Help Desk are to route calls to appropriate agents or departments, provide a wealth of information about various products and services, and conduct problem solving or troubleshooting. In this paper we address the challenges in building this class of applications particularly when speech data is limited or unavailable. We will present the TTS Help Desk as an example of a service that has been deployed for automating the customer care component of the AT&T Labs Natural Voices Business
Cite as: Fabbrizio, G.D., Dutton, D., Gupta, N.K., Hollister, B., Rahim, M., Riccardi, G., Schapire, R., Schroeter, J. (2002) AT&t help desk. Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002), 2681-2684, doi: 10.21437/ICSLP.2002-669
@inproceedings{fabbrizio02_icslp,
author={Giuseppe Di Fabbrizio and Dawn Dutton and Narendra K. Gupta and Barbara Hollister and Mazin Rahim and Giuseppe Riccardi and Robert Schapire and Juergen Schroeter},
title={{AT&t help desk}},
year=2002,
booktitle={Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002)},
pages={2681--2684},
doi={10.21437/ICSLP.2002-669}
}