This is the first post for “With Varying Frequency” that I am speaking rather than typing.
I’m working with a software package called “MacSpeech Dictate” in an effort to learn more about speech recognition by computers.
Obviously through the errors of my speech, and the limits of computer software, there will be some small corrections I’ll need to make before posting this. But for the most part the basic text will all have been spoken.
In the terms of an Amateur Radio Ham’s shack there may be many possibilities for use of speech recognition software. Whether it is to work digital modes, such as PSK, or to control equipment, the potential is boundless.
Setting up the software was fairly easy. It started with setting up the hardware. Then a session of reading into the machine to allow it to become familiar with my voice as what they called a “voice profile,” completed the configuration.
It’s possible to send e-mail messages completely without ever touching the machine. In the case of creating this blog post, I have had to touch the machine to initiate the editor and start the speech recognition software entering text.
Watching the entered text I see that there are six or seven corrections I will need to make before posting this, not bad at all considering I would have made many more typing myself. The biggest risk seems to be that of using English language construction of the spoken form in a written document.
More as I learn to use this technology,