A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

Two-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.

A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.

[CVPR'21] SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data, in PyTorch

Deep-learning-based implementation of the popular Hungarian algorithm that helps solve the assignment problem.