Spoken Language Systems for Wayfinding Information

Spoken language systems, consisting of speech recognition, speech synthesis, natural languageprocessing, and human-computer interfaces allow people to use speech to communicate with computers.This system provides access to wayfinding/route information for the visually impaired. The system isa spoken language system which can recognize the speech of any speaker and requires t=no customhardware. A speaker independent speech recognition system developed during phase I will be the basefor the system. Phase I has two primary goals: 1. demonstrate the feasibility of combining HiddenMarkov Models, Segmental models, and Artificial neural networks to improve recognition performance.We will tightly integrate these technologies in a succinct mathematical framework. 2. We will determinethe needs of visually impaired persons for wayfinding information and use this to design a languagemodel which constrains the recognition process without appearing to constrain the users' interactions.If successful, the technology would permit the development of more powerful, cost-effective spokenlanguage systems than are currently available for making wayfinding information available to personswith visual impairments.