Spoken-language-identification
Spoken-language-identification copied to clipboard
can the trained model process audio with background music or noize?
Hi, I am woking on LID, my online environment is not clean, there are bg musics and noizes. and the accuracy is not satisfying. Is there any solutions for my problem?
I didn't follow the progress in this field, but I assume it's not a solved problem.
You can check 2hz API for denoising, but it's a commercial product.