[iced]

An update on the situation:

I now verified that after setting the audioMode to Default or VideoRecording explicitly, I can play the audio using AirPlay on an Apple TV.

However in my project, I need to play it on a speaker with AirPlay functionality on Airport Express. Thus, there is no video stream.

When using the Default mode or the VideoRecording mode, the Airplay speakers don’t even show up for selection, however the AppleTV does. When set to other audioModes, the speakers show up (as well as the TV) but the audio does not stream to any of them.

I think we need to use voiceChat mode, but I don’t know why it’s not working properly.

[iced]

Btw I don’t mean a specific thing with “harder-to-recognize accent”. My question is if it is possible to perform User-calibration. Thanks

[iced]

Hey Halle,

The topic seemed relevant to my question and I decided to not open a new topic and ask it here.

Is it possible to calibrate OpenEars to recognize some harder-to-recognize English accents?

[iced]

Okay, I’m looking into it and will post what I find.

On the main subject of this thread: Can you please tell if changing vadThreshold while pocketsphinx listens takes effect immediately? Suppose OE starts listening with vadThreshold=2.0. Then all of a sudden with a voice command ‘INCREASE THRESHOLD’, we set vadThreshold to 3.0 by calling the pocketsphinx’s method. Now does this take effect immediately and pocketsphinx resumes listening with vad=3.0? Or would it require another stop/start listening?

[Author]

Posts