New answers tagged

1

It would be enough to divide by three, but dividing by 4 might be faster as it can be just be shifted by two. And yes, if only one 16-bit sine channel is playing, it would make the resulting output sum to have 14 bits precision per channel. The signals could be generated with amplitude 10922 so three of them can just be summed together.


0

The envelope of the time signal, more exactly, the magnitude of the signal's analytic representation, should provide a robust way of fingerprinting. It's robust against phase and with energy normalization also robust against level differences. Even a pitch shifted version of the signal could be detected. As your signals are short, memory and computation time ...


1

You could try something silly like combining the score of a speaker identification algorithm trained on the original speaker with a score from an algorithm that estimates "nasality". This would be doable if you happen to have enough recordings of the original speaker. If not, then you could just use a voice-to-phonemes algorithm (so, the part of ...


0

This is actually an excellent place to start with ML/DNN tools. Noise Reduction, Speech Processing and Recognition are driving a lot of the innovation in sound in this space. Recurrent Neural Networks and LSTM models are good at identifying patterns - which can be useful in this context. https://jmvalin.ca/demo/rnnoise/ If you’ve got an NVIDIA GPU you could ...


3

First of: "AAC" is not a single codec; there's AAC-LC, HE-AAC, and probably a lot more. Since "audio quality" is a perceptive quality, there's no objectively "best" answer. It's, however, very likely that in all direct human comparisons, MP3 at 128 kb/s would fare worst. Also "audio quality" means something very ...


2

after dividing the short values by participant count so it never gets clipped That's not a great idea, you are loosing a lot of SNR this way. I recommend running the processing in floating point are 32-bit fixed point and only reducing it to 16-bit when you create the output of the algorithm I tried reading webRTC AGC modules but it's too complex for me to ...


Top 50 recent answers are included