Talking to a computer

The idea of talking to a computer and it understanding your commands has been going in and out since the seventies. Despite the increasing popularity of text messaging, voice-activated technology will soon be. Because of tiny keyboards and small touch pads, 'big-fingered' adults would rather shout out than type it out.

"Mobile voice-recognition technology now allows people to send text messages to friends by talking instead of typing; to scan through transcriptions of voice mail instead of taking time to listen to them all; to tell their phones what they're looking for on the Web; and, soon, to post to Twitter from their cars by speaking, allowing drivers to keep their eyes on the road."

A number of phone applications, such as ShoutOut now translate speech into text messages and e-mails. Eventually, computer might be able to listen so well, that the computer can anticipate the upcoming commands and sounds. The technology works by listening to a voice, translating it into digital data and then anticipating the next words or sounds. But as of right now, it's more of a guessing game.

Each year the technology and accuracy of these programs advances and improves. But there are some issues to resolve:

1. Background noise- If a person is on a bus or in a busy street, the voice recognition diminishes. Google's Nexus One is a solution to this problem. It has two microphones that records both voice and background noise and then it subtracts the background noise from the voice.

2. No one speaks the same all the time- A computer might not recognize your voice the first time, so the following time you might change your inflection and tone, leading to frustration. Just speak clearly and have a neutral accent.