ICASSP article: An empirical study of Conv-TasNet1 min read

I’m happy to share the highlights of my first paper with Dolby! We will be presenting this work at ICASSP 2020, in Barcelona.

Link to arxiv!

Several improvements have been proposed to Conv-TasNet – that mostly focus on the separator, leaving its encoder/decoder as a (shallow) linear operator. We propose a (deep) non-linear variant of it, that is based on a deep stack of small filters. With this change, we can improve 0.6-0.9 dB SI-SNRi.

The encoder/decoder we propose is based on a deep stack of SMALL filters, and concurrent works have also found that using an encoder/decoder based on SMALL filters works best:

We also challenge the generalisation capabilities of Conv-TasNet. We report a LARGE performance drop when using cross-dataset evaluation. This result is important. It showcases the limitations of the current evaluation setup.

USE CROSS-DATASET EVALUATION IN YOUR PAPERS 🙂