I sometimes have an issue where I launch a command using a Google Now, and it asks for follow-up info (for instance, "What's the message?" when my command was "Send a message to xxx"), but it doesn't start listening for an answer. I can still click on the blank field on the screen and type in my answer, but it kind of defeats the point of voice commands.

Note that it's not systematic: sometimes, the voice recognition will indeed turn on and I will be able to speak my answer.

Is this a known problem, and if so, is there a way to fix it?

  • Probably clarity of voice, consistent vocal speed, careful modulation, reduction of inflection or accented speech. All techniques to reduce vocal input confusion. – wbogacz Jan 16 '16 at 22:22
  • Read again. The problem isn't that it doesn't recognize my voice. The problem is that the listening mechanism doesn't turn on at all. – Timst Jan 17 '16 at 15:20
  • Possibly I'm wrong, and I'm willing to admit it. I'm suggesting that the failure for the voice recognition to process your vocal commands is because of uncertainty that the command is properly issued, or ended, because of my suggestions earlier. I think you need to evaluate the group where the failure occurs is: 1. If name(s) matching is uncertain or inconclusive, 2. Pronunciation is unclear, 3. Inflection makes the voice recognition believe the request is incomplete. Programmed systems don't behave differently, but people employing them do. Evaluate effectively. – wbogacz Jan 17 '16 at 17:05

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.