could it be used in real time ?

Question

could it be used in real time ?

Closed this issue 5 years ago · 4 comments

Dear,
I want to use the method to solve the howling in RTC-Real Time Communication,
so could I separate the noise and voice frame by frame ?

any reference will be appreciated.

thx

Answer 1 · 2019-08-29T08:36:15.000Z

I believe it is possible! I think it might require writing inference code more efficiently and using hardware acceleration.

Answer 2 · 2019-08-29T09:22:56.000Z

So I want to know that whether the input signal length can be modified and which parameter should I change if I need.
thx

Answer 3 · 2019-08-29T09:34:15.000Z

maybe you misunderstand the howling, it's very strong in RTC, like the pic down,

the up is howling and the down voice

Answer 4 · 2019-09-03T10:18:40.000Z

I'm not familiar with this application, but it looks doable when looking at the spectrogram. You might need to check "Work on your data" section in the readme.