This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 United States License.
Conv-TasNet: Surpassing Ideal TimeโFrequency Magnitude Masking for Speech Separation
This repository provides a minimum implementation of the Conv-TasNet model for single-channel speech separation. More details will be updated soon.
If you find this repo helpful, please consider citing:
@article{luo2019conv,
title={Conv-TasNet: Surpassing Ideal Time--Frequency Magnitude Masking for Speech Separation},
author={Luo, Yi and Mesgarani, Nima},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume={27},
number={8},
pages={1256--1266},
year={2019},
publisher={IEEE}
}