I need to control keyboard and mouse actions with my voice. Simon open-source speech recognition software seems like a perfect solution. There is an excellent Youtube tutorial showing how to set up Simon with Scenarios (for Firefox or Mouse control) and Speech Models (that recognize certain audio signals as words that result in a particular action within a scenario) -- https://www.youtube.com/watch?v=ghfMMYNOwXo. I successfully downloaded Simon from the Ubuntu Software center. I was able step through the set-up Wizard to download/install several Scenarios (Firefox, mouse, keyboard) successfully. I am able to find and apparently download/install an appropriate Speech Model as well, but when I return to the Simon Speech Model selection page, the model I just downloaded is not available in the dropdown list. The only option is "do not use a base model," which I believe means there is no voice model present that can recognize the audio signals that emerge from my mouth as words with specific meaning. I have set up the audio input (microphone) and output (speaker) devices correctly, because there are volume indicators and sound generators that appear to work properly. The volume and clarity of my voice is not a problem.
Has anyone out there used Ubuntu Simon to control their mouse or browse Firefox successfully? Can anyone help me figure out how to get a Speech Model to install correctly in Ubuntu Simon? I am running Ubuntu 16.04 LTS.
Thank you!
Adv Reply
Bookmarks