> I'd personally settle for a voice-output-only Glass (maybe with chording for text input to avoid the "talking to yourself crazy person" problem, and with a camera/microphone built in for ambient data gathering).
I pitched exactly that idea to Logitech & Inria in Switzerland about 15 years ago and I agree with you, we could have done that long ago and it is one of the best interfaces that you could have. Think 'personal assistant'.
The general idea was to simply open a voice channel with a server farm somewhere that listens to your ambient audio and pics up cues / clicks and responds with audio.
The project stranded on privacy concerns, and on speech decoding issues that Inria foresaw would be hard to overcome.
I pitched exactly that idea to Logitech & Inria in Switzerland about 15 years ago and I agree with you, we could have done that long ago and it is one of the best interfaces that you could have. Think 'personal assistant'.
The general idea was to simply open a voice channel with a server farm somewhere that listens to your ambient audio and pics up cues / clicks and responds with audio.
The project stranded on privacy concerns, and on speech decoding issues that Inria foresaw would be hard to overcome.