This paper describes how a telephone-based application can perform a variety of tasks in a completely hands-free mode. The overall architecture of the speech component is multimodal in that each mode is tailored to a specific need of the interface. The various modes are described as well as the underlying core technology. To illustrate the effectiveness of the implementation, we present experimental results in American English, UK English and French on a variety of benchmarks, including live data collected during actual use of the system.

A novel system for extracting information from stereotyped voice traffic is described. Off-the-air recordings of commercial air traffic control communications are interpreted in order to identify the flights present and determine the scenario (e.g., takeoff, landing) that they are following. The system combines algorithms from signal segmentation, speaker segregation, speech recognition, natural language parsing, and topic classification into a single system. Initial evaluation of the algorithm on data recorded at Dallas-Fort Worth airport yields performance of 68% detection of flights with 98% precision at an operating point where 76% of the flight identifications are correctly recognized. In tower recording containing both takeoff and landing scenarios, flights are correctly classified as takeoff or landing 94% of the time.< >