AI Enthusiast

@JiajiaGrace Sorry, it is just a picture, not a GUI.

@khrouatbi Install an Ubuntu system. Otherwise, there may be other problems in the future in the Windows.

The same problem. I calculate self.total_samples = 0 while self.len_samples = 15 on my dataset where the length of each audio is less than 15s.

@Rajkashyapmallala Hi, you can set "step=2" in "run.sh" to separate a mixed audio file using trained model.

@akshayaCap Hello, I have uploaded .wav results of 2 speakers - "6-separated_result_BLSTM" and "7-separated_result_LSTM". As you say "with multiple speaker with added noise", one speaker can be regarded as target...

@akshayaCap I'm sorry for sharing the input files. The input dataset WSJ0 needs paid license. There's the [WSJ0 corpus website](https://catalog.ldc.upenn.edu/ldc93s6a) where you can purchase.

@akshayaCap Thanks for your interest in my work. Fisrtly, I haven't done a separation experiment on the VCTK dataset, but you can try it. Secondly, you can just replace one...

Hi, you can read those two files tfrecords_io.py and run_lstm.py.

@pranavj Hi, you can refer to my reference code “snsun/pit-speech-separation” and modify the model parameter "BLSTM" to "LSTM".

@AndyGaogao yes