Hi, I am currently working on a project which requires me to implement the ICA algorithm in real time, to be specific, I am trying to separate the noise from the audio. When I perform the algorithm in offline, it works fine despite the amplitude of the separated audio is a bit soft. However, when I implement it in real-time, the separated audio becomes very soft. Any source code that I could refer to solve this kind of problem. Thanks.
Lee Jun Yang ,
Your problem may be both hardware and software related. Are the sources of audio captured on the same system or sent to a processing system? What are the specs for the system used? Are you using efficient libraries (BLAS, LAPACK or OpenMP)? have you considered implementing ICA on CUDA? Which programming language are you using?
Which solution might be best for you depends on what you are actually using now.
I am going to implement it in a microcontroller, Teensy 4.0. Before I actually implement it, I have run some simulation (in my computer, using the audio file that I have prepared). The separated signal from the simulation is very weak as compare to the target signal.
Lee Jun Yang ,
What you are describing appear to be two different problems, one compounding the other
For the first problem
1) Which ICA implementation are you using?
For the second problem
1) For the real time capture what sampling rate are you doing the capture?
2) what are you using to capture the signal in real time(e.g. are you using ALSA on Linux or are you using Windows)?
Note that the RM Cortex-M7 of the Teensy 4.0 is a slow processor compared to an Intel or AMD