The B3 model in paper - Githubissues

breizhn / DTLN

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

MIT License

585 stars 161 forks source link

The B3 model in paper #31

Open GatsbyChen opened 3 years ago

GatsbyChen commented 3 years ago

Hi，Thank you for your fantastic implement about DTLN! I just want to know more details about model b3 in paper, only one STFT&iFFT and 2*2 lstm layer in b3? what the difference compare to b1?