I want to record a radio stream from an FM radio. The sound of the radio signal will be input to the line input of the computer.
This audio signal contains speech (colloquial words) and music. I want to admit in real time if it is music or speech. Perhaps the frequency will do it. How to implement something like this? I know this Algorithm chain to determine if sound is music , but my problem is simpler.
I hope someone has done something like this or can tell me where to start. The best way to do this is with a program that listens on a line on my computer and sends a change signal to another program or script when it detects a change in speech or music. Another program or script saves the record until it receives a change signal and writes further records.
The goal is to get files containing only music or speech.
source
share