The commoditization of low-power radios, a rich set of sensors, longer-lasting batteries, and feature-rich microcontrollers has prompted significant research efforts to imbue physical environments with the responsiveness and awareness afforded by ubiquitous, unobtrusive, low-maintenance sensor networks. However, despite these technical advances, there has… (More)
This paper presents a field study that compares natural language call routing with standard touch-tone menus. <i>Call routing</i> is the task of getting callers to the right place in the call center, which could be the appropriate live agent or automated service. <i>Natural language</i> call routing lets callers describe the reason for their call in their… (More)
We describe the methods and hardware that we are using to produce a real-time demonstration of an integrated Spoken Language System. We describe algorithms that greatly reduce the computation needed to compute the N-Best sentence hypotheses. To avoid grammar coverage problems we use a fully-connected first-order statistical class grammar. The speech-search… (More)
The DARPA SLS Program is developing a technology that has been justified, at least in part, by its potential relevance to military applications. In an effort to demonstrate the relevance of SIS technology to real-world military applications, BBN has undertaken the task of providing a spoken language interface to DART, a system for military logistical… (More)
This document contains copies of reports prepared for the DARPA Speech and Natural Language Workshop. Included are reports from DARPA/ISTO sponsored programs and other materials prepared for use at the workshop.
This paper describes a method to quantify both cost-effectiveness and (objective) usability of telephone voice user interfaces in a single measure, based on end-to-end recordings of thousands of calls. This method is a valuable tool for usability engineering of commercially deployed, touch-tone and speech-enabled telephone voice user interfaces.
This paper describes a system that empowers practitioners to substantially improve the user experience with call center automation and agents. Unlike other approaches we analyze the caller experience in live calls end-to-end, from dialing to hangup. A web-based solution, the Call Browser provides access to hundreds or thousands of live end-to-end calls, and… (More)
Typically, real-time speech recognition-if achieved at all-is accomplished either by greatly simplifying the processing to be done, or by the use of special-purpose hardware. Each of these approaches has obvious problems. The former results in a substantial loss in accuracy, while the latter often results in obsolete hardware being developed at great… (More)