Not working with this wav (file attached)

[kovalroma]

Hello, I am radio amateur and trying to find solution to detect voice in VHF audio record. I have this sample without voice, but you algorithm detect it.

[marsbroshok]

Hi, the detection algorithm in my code is basic. It checks the energy of voice frequencies (https://en.wikipedia.org/wiki/Voice_frequency) and use it to "detect" speech. I guess in your case there is noise in the speech frequencies as well so there is some energy and it triggers the detection.

I'm not working on this project anymore. I advise everyone curious about voice detection to have a look at some more modern approaches using deep learning, like:

• https://www.mathworks.com/help/audio/examples/voice-activity-detection-in-noise-using-deep-learning.html
• https://medium.com/vivolab/vivovad-a-voice-activity-detection-tool-based-on-recurrent-neural-networks-32356526321c
• https://github.com/hcmlab/vadnet

[RicherMans]

Hey there, I don't want to hijack your work here @marsbroshok , but I just came across this post randomly and would like to propose my recent work using weakly supervised training as a possible solution.
@kovalroma if you like, check out GPVAD

I also ran your file over my model, it predicts correctly nothing.