Downgrading to older versions of OpenEars

Home Forums OpenEars Downgrading to older versions of OpenEars

Viewing 2 posts - 1 through 2 (of 2 total)

  • Author
  • #1030679

    I have an issue that Open Ears recognizes background speech as well as user interactions. More specific, it recognizes when I speak from a distance, as well as when I speak directly into the mic. When there is background speech, it gets recognized along with direct speech into the mic. It’s really not a problem with the Open Ears framework, as it was made to be flexible with different noise levels.
    The requirements of my app are really specific. It needs to recognize what the user says only when they speak directly into the microphone (so that normal speech isn’t also recognized). The background noise level is pretty constant. Is there a way to recognize voice only when audio level is loud enough? I’ve tried changing VAD Threshold, but it is still too sensitive, especially when it is quiet.
    Recently, I read about a similar problem in this blog post:
    It seems that Open Ears 1.x isn’t as sensitive to background noise as OpenEars 2.x. If I’m correct, version 1.7 worked better in their case, and didn’t recognize the unwanted background noises.
    Is there a link to download older versions of Open Ears? If so that would be great. I would like to try different versions to see which works better for the purpose of my app.


    Halle Winkler


    Sorry, there is no link or support for using an older version. The older version of OpenEars wasn’t less sensitive to background noise (there are actually many older discussions in these forums about how to reduce its noise sensitivity), it just had a (very slightly) higher voice activity threshold setting, but which couldn’t be adjusted.

    You can raise vadThreshold in OpenEars 2.x in order to get the same results, but also have the flexibility to set it to your usage scenario’s ideal setting. There is more info in the FAQ and 2.x-related posts in the forums about using vadThreshold and/or possibly Rejecto to ameliorate non-speech and out-of-vocabulary input.

Viewing 2 posts - 1 through 2 (of 2 total)
  • You must be logged in to reply to this topic.