Hot answers tagged

1

This does sound like a job for cross correlation. It's quite robust and some tweaking with the threshold value should give you the result you are looking for. It's calculated in the time domain, so no spectrum or spectrogram fiddling neccessary. Basically, you just "slide" your sample over the recorded audio and do a convolution of the overlapping ...


Only top voted, non community-wiki answers of a minimum length are eligible