topic Re: Classifying audio files in Discussions

Classifying audio files

Sop — Thu, 08 Jun 2023 16:37:39 GMT

Is there a way to process raw audio files with or without metadata? Having a microphone installed to detect noise is a cheap way to protect equipment and personnel from damage. However, it would be much more efficient if the sound is classified (as being false alarm, object loose etc). Can a model be trained in JMP for that purpose?

Re: Classifying audio files

Jed_Campbell — Thu, 09 Feb 2023 16:01:27 GMT

This blog entry might get you started.

Re: Classifying audio files

Craige_Hales — Thu, 09 Feb 2023 16:36:41 GMT

or which is close to what you describe. So is .

Are you opening a file or looking at a never-ending stream, maybe over a socket connection?

I've been through several iterations on wav files with JMP; it is a complicated format. If you constrain the wav file input to 44.1kHz stereo, for example, you can simplify some things. You might even get away with skipping several hundred bytes and treating the rest of the file as samples. You could also use Python to read the samples and pass them back to JMP.

I've never gotten serious about training models, but I imagine using the FFT to move the signal from time domain to frequency domain would be a good first step. The FFT lets you think about the frequencies that were present during a time slice.

Sounds like a fun project, be great to hear more about it!