Link to home
Start Free TrialLog in
Avatar of Francois Koutchouk
Francois KoutchoukFlag for United States of America

asked on

Looking for the equivalent to OpenCV for audio streams

I would like to recognize sounds within an audio stream.  For instance, a doorbell.
Basically it would be the equivalent to using OpenCV to identify a face within a video stream.
So I am looking for the equivalent of an OpenCV library for audio (rather than images/video).  Or perhaps some cloud-based solution -- although I have not see anything on AWS or Azure.
Avatar of Kyle Santos
Kyle Santos
Flag of United States of America image

Hi,

I am following up on your question.  Do you still need help?

If you solved the problem on your own, would you please post the solution here in case others have the same problem?

Regards,

Kyle Santos
Customer Relations
Avatar of Francois Koutchouk

ASKER

I haven't solved the problem.  I am surprised there is so much available on video/image analysis (OpenCV) and so little on the... audio portion of the video!
Hi Francois,

Would you like me to send alerts to more experts to try and help you here?
Yes, I would love to see a solution to that.  I reached out to one of the expert on OpenCV who told me he was not interested in the audio aspect...  I think there is a whole area to explore, what with all those AI discussions these days. Thank you,
I have only just started playing with this, I think https://github.com/BrainJS/brain.js or https://www.tensorflow.org/ is what you are after.
If I were going to attempt this, I'd likely use a speech recognition system.

Try searching for speech recognition ubuntu OR github + pick a system + then train the system to recognize your doorbell or any other sounds you're targeting to parse/recognize.
This question needs an answer!
Become an EE member today
7 DAY FREE TRIAL
Members can start a 7-Day Free trial then enjoy unlimited access to the platform.
View membership options
or
Learn why we charge membership fees
We get it - no one likes a content blocker. Take one extra minute and find out why we block content.