Speech Dialogue on a Raspberry Pi using Python and Pocket Sphinx

[squirrel1]

Hi. I am writing a Raspberry Pi project in Python that creates dialogue between the machine and the user. It is used offline so I am using Pocket Sphinx.

I have been unable to prove that this technology is capable of both speech-to-text and text-to-speech in the same application. They work fine alone but I'm first trying to have the raspberry pi restate what the user said in the form of "Did you say...." Part of my problem is that it must be multithreaded because it must both monitor input from the speaker and also from external messages to deliver to the speaker.

Has someone out there solved this problem? Is this technology capable of this interactive speech? I'd appreciate any help!

[squirrel1]

Hello? Can someone out there please help me with my problem? I need to establish a spoken dialogue between the user and the Raspberry Pi based on input from multiple sources. Thanks!

[dhdaines]

Hi, this is an interesting problem, but not actually a bug in PocketSphinx, and without being able to look at your code there's unfortunately no chance at all that anyone can help you with your problem.

I'm converting this to a discussion.