-
Automated Controls & Systems
Distance: 5.9 Mi955 Lively Blvd.
60191 Wood Dale -
Progressive Communications, Inc
Distance: 10.6 Mi1072 N Garfield St
60148-1336 Lombard -
Commeg Systems, Inc.
Distance: 12.1 Mi141 W Home Ave
60181 Villa Park -
Control Systems Inc
Distance: 13.3 Mi226 Terrace Dr
60060 Mundelein -
Liquid Controls Inc
Distance: 16.3 Mi105 Albrecht Dr
60044-2252 Lake Bluff
Website Links
Description
this is what is the current interface. You manipulation a pointer on a screen. You type in text. A big jump would be to interact via speaking. Also, use of gestures to manipulate objects around you. A computer that could understand and respond to a human speaker would go a long way to improve the interface. There are some initial efforts such as in mobile phones operating in response to a person speaking. And there are some speaking to text software for the personal computer. But these are difficult to always operate accurately. A computer that had a true 3-dimensional interface would also help. Here you could look at information, objects and other people in a more natural way. There is millions of years of evolution for the development of two eyes for the 3-dimensional world. The personal computer market leader for desktop speech recognition software is Dragon NaturallySpeaking. It is designed to run on Microsoft Windows, but has also been shown to run under Linux using software emulation. This has been reviewed in Wikipedia:NaturallySpeaking . NaturallySpeaking has to be trained for approximately 10 minutes to recognize the user's voice. Initially, accuracy rates of 80-85% are reasonable to be expected. An expert NaturallySpeaking user can expect 98-99% recognition accuracy according to Nuance Communications, but such claims of almost perfect accuracy have never been substantiated independently. Moreover, the program itself very carefully avoids reporting on recognition rates. The 98-99% figures are unlikely to be true. So a recognition rate of 90 % is to be expected in a reasonable time. This is missing 1 word in 10 and would make a speech interface tedious. This rate would degrade in noisy environments.