Detect level (RMS) of recognized speech

Home › Forums › OpenEars › Detect level (RMS) of recognized speech

Viewing 5 posts - 1 through 5 (of 5 total)
Advertisement: “Did you know OpenEars™ can use rules-based grammars to recognize fixed phrases? And RuleORama lets you use them with RapidEars!”

  • Author
    Posts
  • April 3, 2014 at 11:55 pm #1020682
    ggjunker
    Participant

    Is there a way with the offline speech detection?

    April 4, 2014 at 12:02 am #1020683
    Halle Winkler
    Politepix

    Welcome,

    Sure, take a look at the sample app for level reading of incoming audio.

    April 4, 2014 at 12:25 am #1020684
    ggjunker
    Participant

    A HA!

    [self.pocketsphinxController pocketsphinxInputLevel]]

    I knew I had seen it somewhere before, but after running the OpenEarsSampleApp awhile ago I had been working only with the tutorial code, which skips that part.

    Thanks Halle!

    April 5, 2014 at 12:44 am #1020695
    ggjunker
    Participant

    Got it working, thanks. Just one question — is the level reported averaged over the 500ms or so that it takes that method to return? Or is it taking a point sample somewhere in that window of time?

    April 5, 2014 at 9:41 am #1020697
    Halle Winkler
    Politepix

    It’s an average of point samples.

  • Author
    Posts
Viewing 5 posts - 1 through 5 (of 5 total)
  • You must be logged in to reply to this topic.