This is the repo of the manuscript "WDASnet: weighted-direction-aware speech separation network in multi-people meeting environment", which was submitted to Interspeech2022. The network code has been released and you can train it with your own pipeline.
The demos are available at https://yangyi0818.github.io/WDASNet/
The code has been rearranged recently. If you have any advice or questions, please feel free to contact me.