News for hackers. Stuff that matters.
Re:Deep Learning ‘ahem’ detector by zump on Wednesday November 09, 2016 @07:11AM (#12909586)
How does this work when the spectrogram is finite time slice?!
Re:Deep Learning ‘ahem’ detector by skoocda on Monday November 14, 2016 @12:01AM (#12947667)
Lots of overlapping. It's a sliding window function. Ballpark for most algorithms: 10 ms of new audio, 90 ms of old audio.